{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "Spacy - Aula 5 - Python para PLN.ipynb", "provenance": [], "collapsed_sections": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "5Eou-fvY7awQ" }, "source": [ "# Instalação do Spacy\n", "\n", "Primeiro precisamos atualizar o spacy que já está instalado no colab.\n", "\n", "A versão que está disponível não dá suporte ao modelo de dados em portugues.\n", "\n", "https://spacy.io/usage" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-BqxDKI1FVo4", "outputId": "5f03407e-d81a-43a4-cab2-ee7e59b75ca1" }, "source": [ "pip install -U spacy" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: spacy in /usr/local/lib/python3.7/dist-packages (2.2.4)\n", "Collecting spacy\n", " Downloading spacy-3.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.9 MB)\n", "\u001b[K |████████████████████████████████| 5.9 MB 5.2 MB/s \n", "\u001b[?25hCollecting pathy>=0.3.5\n", " Downloading pathy-0.6.0-py3-none-any.whl (42 kB)\n", "\u001b[K |████████████████████████████████| 42 kB 1.5 MB/s \n", "\u001b[?25hCollecting pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4\n", " Downloading pydantic-1.8.2-cp37-cp37m-manylinux2014_x86_64.whl (10.1 MB)\n", "\u001b[K |████████████████████████████████| 10.1 MB 20.2 MB/s \n", "\u001b[?25hRequirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy) (3.0.5)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.7/dist-packages (from spacy) (2.11.3)\n", "Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (1.19.5)\n", "Collecting typer<0.5.0,>=0.3.0\n", " Downloading typer-0.4.0-py3-none-any.whl (27 kB)\n", "Collecting catalogue<2.1.0,>=2.0.6\n", " Downloading catalogue-2.0.6-py3-none-any.whl (17 kB)\n", "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (4.62.3)\n", "Collecting thinc<8.1.0,>=8.0.9\n", " Downloading thinc-8.0.10-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (623 kB)\n", "\u001b[K |████████████████████████████████| 623 kB 53.0 MB/s \n", "\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (21.0)\n", "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (2.23.0)\n", "Requirement already satisfied: typing-extensions<4.0.0.0,>=3.7.4 in /usr/local/lib/python3.7/dist-packages (from spacy) (3.7.4.3)\n", "Collecting spacy-legacy<3.1.0,>=3.0.8\n", " Downloading spacy_legacy-3.0.8-py2.py3-none-any.whl (14 kB)\n", "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy) (2.0.5)\n", "Collecting srsly<3.0.0,>=2.4.1\n", " Downloading srsly-2.4.1-cp37-cp37m-manylinux2014_x86_64.whl (456 kB)\n", "\u001b[K |████████████████████████████████| 456 kB 42.3 MB/s \n", "\u001b[?25hRequirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from spacy) (57.4.0)\n", "Requirement already satisfied: blis<0.8.0,>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (0.4.1)\n", "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.7/dist-packages (from spacy) (1.0.5)\n", "Requirement already satisfied: wasabi<1.1.0,>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from spacy) (0.8.2)\n", "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from catalogue<2.1.0,>=2.0.6->spacy) (3.5.0)\n", "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->spacy) (2.4.7)\n", "Requirement already satisfied: smart-open<6.0.0,>=5.0.0 in /usr/local/lib/python3.7/dist-packages (from pathy>=0.3.5->spacy) (5.2.1)\n", "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (2.10)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (2021.5.30)\n", "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (3.0.4)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy) (1.24.3)\n", "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.7/dist-packages (from typer<0.5.0,>=0.3.0->spacy) (7.1.2)\n", "Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.7/dist-packages (from jinja2->spacy) (2.0.1)\n", "Installing collected packages: catalogue, typer, srsly, pydantic, thinc, spacy-legacy, pathy, spacy\n", " Attempting uninstall: catalogue\n", " Found existing installation: catalogue 1.0.0\n", " Uninstalling catalogue-1.0.0:\n", " Successfully uninstalled catalogue-1.0.0\n", " Attempting uninstall: srsly\n", " Found existing installation: srsly 1.0.5\n", " Uninstalling srsly-1.0.5:\n", " Successfully uninstalled srsly-1.0.5\n", " Attempting uninstall: thinc\n", " Found existing installation: thinc 7.4.0\n", " Uninstalling thinc-7.4.0:\n", " Successfully uninstalled thinc-7.4.0\n", " Attempting uninstall: spacy\n", " Found existing installation: spacy 2.2.4\n", " Uninstalling spacy-2.2.4:\n", " Successfully uninstalled spacy-2.2.4\n", "Successfully installed catalogue-2.0.6 pathy-0.6.0 pydantic-1.8.2 spacy-3.1.3 spacy-legacy-3.0.8 srsly-2.4.1 thinc-8.0.10 typer-0.4.0\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "RpafPx4v7qP2" }, "source": [ "**Depois de instalar precisamos baixar os pacotes complementares**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "zS1JfXlBF42u", "outputId": "5698d623-fd41-44d0-a371-4b9400bf04fb" }, "source": [ "pip install -U spacy-lookups-data" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting spacy-lookups-data\n", " Downloading spacy_lookups_data-1.0.2-py2.py3-none-any.whl (97.3 MB)\n", "\u001b[K |████████████████████████████████| 97.3 MB 66 kB/s \n", "\u001b[?25hRequirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from spacy-lookups-data) (57.4.0)\n", "Installing collected packages: spacy-lookups-data\n", "Successfully installed spacy-lookups-data-1.0.2\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "MmiMoEVv7wMO" }, "source": [ "**E finalmente instalamos o modelo de língua disponibilizado pelo spaCy**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "6duQFrspGHvZ", "outputId": "091b942d-b14a-4d45-fced-1956fded684c" }, "source": [ "!python -m spacy download pt_core_news_lg\n", "#!python -m spacy download pt_core_news_md\n", "#!python -m spacy download pt_core_news_sm" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting pt-core-news-lg==3.1.0\n", " Downloading https://github.com/explosion/spacy-models/releases/download/pt_core_news_lg-3.1.0/pt_core_news_lg-3.1.0-py3-none-any.whl (576.7 MB)\n", "\u001b[K |████████████████████████████████| 576.7 MB 19 kB/s \n", "\u001b[?25hRequirement already satisfied: spacy<3.2.0,>=3.1.0 in /usr/local/lib/python3.7/dist-packages (from pt-core-news-lg==3.1.0) (3.1.3)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (57.4.0)\n", "Requirement already satisfied: wasabi<1.1.0,>=0.8.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (0.8.2)\n", "Requirement already satisfied: pathy>=0.3.5 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (0.6.0)\n", "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (4.62.3)\n", "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.23.0)\n", "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.0.6)\n", "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (3.0.5)\n", "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (1.0.5)\n", "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.8 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (3.0.8)\n", "Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (1.19.5)\n", "Requirement already satisfied: thinc<8.1.0,>=8.0.9 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (8.0.10)\n", "Requirement already satisfied: srsly<3.0.0,>=2.4.1 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.4.1)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (21.0)\n", "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.0.5)\n", "Requirement already satisfied: typing-extensions<4.0.0.0,>=3.7.4 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (3.7.4.3)\n", "Requirement already satisfied: blis<0.8.0,>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (0.4.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.11.3)\n", "Requirement already satisfied: typer<0.5.0,>=0.3.0 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (0.4.0)\n", "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.9.0,>=1.7.4 in /usr/local/lib/python3.7/dist-packages (from spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (1.8.2)\n", "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from catalogue<2.1.0,>=2.0.6->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (3.5.0)\n", "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.4.7)\n", "Requirement already satisfied: smart-open<6.0.0,>=5.0.0 in /usr/local/lib/python3.7/dist-packages (from pathy>=0.3.5->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (5.2.1)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (1.24.3)\n", "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.10)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2021.5.30)\n", "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (3.0.4)\n", "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.7/dist-packages (from typer<0.5.0,>=0.3.0->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (7.1.2)\n", "Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.7/dist-packages (from jinja2->spacy<3.2.0,>=3.1.0->pt-core-news-lg==3.1.0) (2.0.1)\n", "Installing collected packages: pt-core-news-lg\n", "Successfully installed pt-core-news-lg-3.1.0\n", "\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n", "You can now load the package via spacy.load('pt_core_news_lg')\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "9W9NiF0g742N" }, "source": [ "**Agora, o uso efetivo da biblioteca**" ] }, { "cell_type": "code", "metadata": { "id": "Y3BsZEUkI3E_" }, "source": [ "import spacy\n", "\n", "# Um texto de exemplo\n", "texto = \"Para políticos e infectologistas, a opção de Michelle de se 10 vacinar nos EUA, não no Brasil, 2021 é um absurdo e um desprezo ao SUS (Sistema Único de Saúde) e ao PNI (Programa Nacional de Imunizações).\"\n", "\n", "# Carregamos o modelo de língua que baixamos\n", "nlp = spacy.load(\"pt_core_news_lg\")\n", "\n", "# Usamos o modelo para analisar o nosso texto :)\n", "doc = nlp(texto)" ], "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "metadata": { "id": "syWfeowp8KOG" }, "source": [ "**Usando a variável \"doc\" podemos acessar os tokens e as diversas análises feitas pelo spaCy**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "j4dPg3ygJb1U", "outputId": "dedd3e90-1e2b-49e0-c5a1-1b88ff2154b7" }, "source": [ "# geração da lista de tokens (tokenização)\n", "\n", "# Observe que essa estrutura pode ser convertida para a seguinte:\n", "# tokens = []\n", "# for token in tokens:\n", "# tokens.append(token)\n", "\n", "tokens = [token for token in doc]\n", "tokens" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "[Para,\n", " políticos,\n", " e,\n", " infectologistas,\n", " ,,\n", " a,\n", " opção,\n", " de,\n", " Michelle,\n", " de,\n", " se,\n", " vacinar,\n", " nos,\n", " EUA,\n", " ,,\n", " não,\n", " no,\n", " Brasil,\n", " ,,\n", " é,\n", " um,\n", " absurdo,\n", " e,\n", " um,\n", " desprezo,\n", " ao,\n", " SUS,\n", " (,\n", " Sistema,\n", " Único,\n", " de,\n", " Saúde,\n", " ),\n", " e,\n", " ao,\n", " PNI,\n", " (,\n", " Programa,\n", " Nacional,\n", " de,\n", " Imunizações,\n", " ),\n", " .]" ] }, "metadata": {}, "execution_count": 8 } ] }, { "cell_type": "markdown", "metadata": { "id": "bw_4X5aS8jXm" }, "source": [ "**Salvando na lista o texto dos tokens:** ***.orth_***" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "obXc62cgK0IW", "outputId": "87e77bd0-f505-46a5-8471-438b3e137927" }, "source": [ "tokens = [token.orth_ for token in doc]\n", "tokens" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "['Para',\n", " 'políticos',\n", " 'e',\n", " 'infectologistas',\n", " ',',\n", " 'a',\n", " 'opção',\n", " 'de',\n", " 'Michelle',\n", " 'de',\n", " 'se',\n", " 'vacinar',\n", " 'nos',\n", " 'EUA',\n", " ',',\n", " 'não',\n", " 'no',\n", " 'Brasil',\n", " ',',\n", " 'é',\n", " 'um',\n", " 'absurdo',\n", " 'e',\n", " 'um',\n", " 'desprezo',\n", " 'ao',\n", " 'SUS',\n", " '(',\n", " 'Sistema',\n", " 'Único',\n", " 'de',\n", " 'Saúde',\n", " ')',\n", " 'e',\n", " 'ao',\n", " 'PNI',\n", " '(',\n", " 'Programa',\n", " 'Nacional',\n", " 'de',\n", " 'Imunizações',\n", " ')',\n", " '.']" ] }, "metadata": {}, "execution_count": 10 } ] }, { "cell_type": "markdown", "metadata": { "id": "KS_T4hTJ89VW" }, "source": [ "**Demais atributos**\n", "\n", "\n", "* .is_apha\n", "* .is_digit\n", "* .is_punct\n", "\n", "https://spacy.io/api/token#attributes\n", "\n" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-tOljq2VLUzW", "outputId": "d416ea2c-bf4d-46b5-dbdc-afe83aecd0a1" }, "source": [ "alpha_tokens = [token.orth_ for token in doc if token.is_alpha]\n", "print(\"Alpha Tokens: %s \" % (alpha_tokens))\n", "\n", "digit_tokens = [token.orth_ for token in doc if token.is_digit]\n", "print(\"Digit Tokens: %s \" % (digit_tokens))\n", "\n", "punct_tokens = [token.orth_ for token in doc if token.is_punct]\n", "print(\"Punct Tokens: %s \" % (punct_tokens))" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Alpha Tokens: ['Para', 'políticos', 'e', 'infectologistas', 'a', 'opção', 'de', 'Michelle', 'de', 'se', 'vacinar', 'nos', 'EUA', 'não', 'no', 'Brasil', 'é', 'um', 'absurdo', 'e', 'um', 'desprezo', 'ao', 'SUS', 'Sistema', 'Único', 'de', 'Saúde', 'e', 'ao', 'PNI', 'Programa', 'Nacional', 'de', 'Imunizações'] \n", "Digit Tokens: ['10', '2021'] \n", "Punct Tokens: [',', ',', ',', '(', ')', '(', ')', '.'] \n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "FkaK9ex59dg-" }, "source": [ "**Vamos trabalhar com nosso corpus de teste :)**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 221 }, "id": "0Xs4veraNq5h", "outputId": "f70ff0c3-593d-428b-8ded-0bbaef6f38ba" }, "source": [ "corpus = open('/content/drive/MyDrive/recursos/corpus_teste.txt').read()\n", "corpus" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'Giants batem os Patriots no Super Bowl XLII\\nAzarões acabam com a invencibilidade de New England e ficam com o título da temporada\\n04/02/2008 - 01h07m - Atualizado em 04/02/2008 - 09h49m\\n\\nCom um passe de Eli Manning para Plaxico Burress a 39 segundos do fim, o New York Giants anotou o touchdown decisivo e derrubou o favorito New England Patriots por 17 a 14 neste domingo, em Glendale, no Super Bowl XLII. O resultado, uma das maiores zebras da história do Super Bowl, acabou com a temporada perfeita de Tom Brady e companhia, que esperavam fazer história ao levantar o troféu da NFL sem sofrer uma derrota no ano. \\n\\nA vitória dos Giants, porém, também ficará para a história. Pela primeira vez, irmãos quarterbacks triunfam no Super Bowl em temporadas consecutivas. No ano passado, Peyton Manning, irmão de Eli, chegou ao título máximo da NFL pelo Indianapolis Colts.\\n\\nA partida\\n\\nOs Giants começaram com a posse de bola, e mostraram logo que iriam alongar ao máximo suas posses de bola. Misturando corridas com Brandon Jacobs e passes curtos, o time de Nova York chegou à red zone logo na primeira campanha. O avanço, no entanto, parou na linha de 17 jardas e Lawrence Tynes converteu o field goal de 32 jardas para abrir o placar.\\n\\nEli Manning e companhia ficaram 9m54s com a bola, mas o ataque dos Patriots não entrou em campo frio. Logo no retorno do kickoff, o running back Laurence Maroney avançou 43 jardas, deixando Tom Brady em boa posição. Com passes curtos, os Patriots chegaram à linha de 17 jardas e, graças a uma penalidade (interferência de passe) do linebacker Antonio Pierce, alcançaram a linha de uma jarda. Maroney avançou pelo chão e anotou o primeiro touchdown do jogo.\\n\\nOs Giants pareciam rumo à virada na campanha seguinte. Manning achou Amani Toomer para um avanço de 38 jardas, e o time de Nova York entrou novamente na red zone. Com a bola na linha de 14 jardas dos Patriots, os Giants sofreram um revés. Manning passou para Steve Smith, que soltou a bola. Ellis Hobbs aproveitou, tomou a posse para os Patriots, e avançou 23 jardas. \\n\\nA defesa de Nova York manteve o jogo equilibrado. Com dois sacks seguidos, os Giants forçaram o punt e recuperaram a bola. Mas a campanha seguinte provou ser outra decepção para Nova York. O time chegou à linha de 25 jardas, mas Manning sofreu um sack e cometeu um fumble, e o ataque voltou para a linha de 39 jardas, não conseguindo pontuar mais uma vez.\\n\\nOs Patriots tiveram uma última chance de marcar antes do intervalo, mas, a 22 segundos do fim do segundo período, Brady foi novamente sacado. Desta vez, ele cometeu o fumble e os Giants tomaram a posse de bola. Manning tentou um passe longo, de 50 jardas, nos últimos segundos, mas não teve sucesso. \\n\\nO jogo continuou amarrado no terceiro quarto, com as defesas levando a melhor sobre os ataques. A única chance de pontuar do período foi dos Patriots, que chegaram à linha de 31 jardas dos Giants. O técnico Bill Bellichick, porém, optou por uma quarta descida em vez de um field goal. Brady tentou um passe para Jabar Gaffney, mas não conseguiu completar.\\n\\nO último período começou arrasador para os Giants. na primeira jogada, Manning achou o tight end Kevin Boss, para um incrível avanço de 45 jardas, que deixou o time na linha de 35 dos Patriots. Outro lançamento, desta vez para Steve Smith, marcou o avanço até a linha de 12 jardas. Duas jogadas depois, David Tyree pegou um passe de cinco jardas na end zone para anotar o touchdown e virar o jogo.\\n\\nNa hora da decisão, o ataque dos Patriots voltou a funcionar. Com uma série de passes curtos e variados, Brady achou Wes Welker, Randy Moss e Kevin Faulk seguidas vezes até chegar à red zone. A 2m45s do fim, o quarterback conectou mais uma vez com Moss, que se desmarcou e ficou livre na lateral direita da end zone.\\n\\nQuando os fãs de New England já comemoravam a vitória, o inesperado aconteceu. Em uma jogada incrível, Eli Manning se soltou de dois marcadores que o seguravam pela camisa e, na corrida, lançou para Amani Toomer. O wide receiver, bem marcado, saltou e conseguiu a fazer recepção para um avanço de 32 jardas, deixando os Giants na linha de 24 de New England.\\n\\nQuatro jogadas depois, a 39 segundos do fim, Manning achou Plaxico Burress na end zone para conseguir o touchdown do título.'" ] }, "metadata": {}, "execution_count": 17 } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "RUXE-cGMOBqf", "outputId": "15e371e0-bb0a-4d1f-b61d-7c8baa565957" }, "source": [ "import spacy\n", "\n", "nlp = spacy.load(\"pt_core_news_lg\")\n", "doc = nlp(corpus)\n", "\n", "tokens = [token.orth_ for token in doc]\n", "tokens" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "['Giants',\n", " 'batem',\n", " 'os',\n", " 'Patriots',\n", " 'no',\n", " 'Super',\n", " 'Bowl',\n", " 'XLII',\n", " '\\n',\n", " 'Azarões',\n", " 'acabam',\n", " 'com',\n", " 'a',\n", " 'invencibilidade',\n", " 'de',\n", " 'New',\n", " 'England',\n", " 'e',\n", " 'ficam',\n", " 'com',\n", " 'o',\n", " 'título',\n", " 'da',\n", " 'temporada',\n", " '\\n',\n", " '04/02/2008',\n", " '-',\n", " '01h07',\n", " 'm',\n", " '-',\n", " 'Atualizado',\n", " 'em',\n", " '04/02/2008',\n", " '-',\n", " '09h49',\n", " 'm',\n", " '\\n\\n',\n", " 'Com',\n", " 'um',\n", " 'passe',\n", " 'de',\n", " 'Eli',\n", " 'Manning',\n", " 'para',\n", " 'Plaxico',\n", " 'Burress',\n", " 'a',\n", " '39',\n", " 'segundos',\n", " 'do',\n", " 'fim',\n", " ',',\n", " 'o',\n", " 'New',\n", " 'York',\n", " 'Giants',\n", " 'anotou',\n", " 'o',\n", " 'touchdown',\n", " 'decisivo',\n", " 'e',\n", " 'derrubou',\n", " 'o',\n", " 'favorito',\n", " 'New',\n", " 'England',\n", " 'Patriots',\n", " 'por',\n", " '17',\n", " 'a',\n", " '14',\n", " 'neste',\n", " 'domingo',\n", " ',',\n", " 'em',\n", " 'Glendale',\n", " ',',\n", " 'no',\n", " 'Super',\n", " 'Bowl',\n", " 'XLII',\n", " '.',\n", " 'O',\n", " 'resultado',\n", " ',',\n", " 'uma',\n", " 'das',\n", " 'maiores',\n", " 'zebras',\n", " 'da',\n", " 'história',\n", " 'do',\n", " 'Super',\n", " 'Bowl',\n", " ',',\n", " 'acabou',\n", " 'com',\n", " 'a',\n", " 'temporada',\n", " 'perfeita',\n", " 'de',\n", " 'Tom',\n", " 'Brady',\n", " 'e',\n", " 'companhia',\n", " ',',\n", " 'que',\n", " 'esperavam',\n", " 'fazer',\n", " 'história',\n", " 'ao',\n", " 'levantar',\n", " 'o',\n", " 'troféu',\n", " 'da',\n", " 'NFL',\n", " 'sem',\n", " 'sofrer',\n", " 'uma',\n", " 'derrota',\n", " 'no',\n", " 'ano',\n", " '.',\n", " '\\n\\n',\n", " 'A',\n", " 'vitória',\n", " 'dos',\n", " 'Giants',\n", " ',',\n", " 'porém',\n", " ',',\n", " 'também',\n", " 'ficará',\n", " 'para',\n", " 'a',\n", " 'história',\n", " '.',\n", " 'Pela',\n", " 'primeira',\n", " 'vez',\n", " ',',\n", " 'irmãos',\n", " 'quarterbacks',\n", " 'triunfam',\n", " 'no',\n", " 'Super',\n", " 'Bowl',\n", " 'em',\n", " 'temporadas',\n", " 'consecutivas',\n", " '.',\n", " 'No',\n", " 'ano',\n", " 'passado',\n", " ',',\n", " 'Peyton',\n", " 'Manning',\n", " ',',\n", " 'irmão',\n", " 'de',\n", " 'Eli',\n", " ',',\n", " 'chegou',\n", " 'ao',\n", " 'título',\n", " 'máximo',\n", " 'da',\n", " 'NFL',\n", " 'pelo',\n", " 'Indianapolis',\n", " 'Colts',\n", " '.',\n", " '\\n\\n',\n", " 'A',\n", " 'partida',\n", " '\\n\\n',\n", " 'Os',\n", " 'Giants',\n", " 'começaram',\n", " 'com',\n", " 'a',\n", " 'posse',\n", " 'de',\n", " 'bola',\n", " ',',\n", " 'e',\n", " 'mostraram',\n", " 'logo',\n", " 'que',\n", " 'iriam',\n", " 'alongar',\n", " 'ao',\n", " 'máximo',\n", " 'suas',\n", " 'posses',\n", " 'de',\n", " 'bola',\n", " '.',\n", " 'Misturando',\n", " 'corridas',\n", " 'com',\n", " 'Brandon',\n", " 'Jacobs',\n", " 'e',\n", " 'passes',\n", " 'curtos',\n", " ',',\n", " 'o',\n", " 'time',\n", " 'de',\n", " 'Nova',\n", " 'York',\n", " 'chegou',\n", " 'à',\n", " 'red',\n", " 'zone',\n", " 'logo',\n", " 'na',\n", " 'primeira',\n", " 'campanha',\n", " '.',\n", " 'O',\n", " 'avanço',\n", " ',',\n", " 'no',\n", " 'entanto',\n", " ',',\n", " 'parou',\n", " 'na',\n", " 'linha',\n", " 'de',\n", " '17',\n", " 'jardas',\n", " 'e',\n", " 'Lawrence',\n", " 'Tynes',\n", " 'converteu',\n", " 'o',\n", " 'field',\n", " 'goal',\n", " 'de',\n", " '32',\n", " 'jardas',\n", " 'para',\n", " 'abrir',\n", " 'o',\n", " 'placar',\n", " '.',\n", " '\\n\\n',\n", " 'Eli',\n", " 'Manning',\n", " 'e',\n", " 'companhia',\n", " 'ficaram',\n", " '9m54s',\n", " 'com',\n", " 'a',\n", " 'bola',\n", " ',',\n", " 'mas',\n", " 'o',\n", " 'ataque',\n", " 'dos',\n", " 'Patriots',\n", " 'não',\n", " 'entrou',\n", " 'em',\n", " 'campo',\n", " 'frio',\n", " '.',\n", " 'Logo',\n", " 'no',\n", " 'retorno',\n", " 'do',\n", " 'kickoff',\n", " ',',\n", " 'o',\n", " 'running',\n", " 'back',\n", " 'Laurence',\n", " 'Maroney',\n", " 'avançou',\n", " '43',\n", " 'jardas',\n", " ',',\n", " 'deixando',\n", " 'Tom',\n", " 'Brady',\n", " 'em',\n", " 'boa',\n", " 'posição',\n", " '.',\n", " 'Com',\n", " 'passes',\n", " 'curtos',\n", " ',',\n", " 'os',\n", " 'Patriots',\n", " 'chegaram',\n", " 'à',\n", " 'linha',\n", " 'de',\n", " '17',\n", " 'jardas',\n", " 'e',\n", " ',',\n", " 'graças',\n", " 'a',\n", " 'uma',\n", " 'penalidade',\n", " '(',\n", " 'interferência',\n", " 'de',\n", " 'passe',\n", " ')',\n", " 'do',\n", " 'linebacker',\n", " 'Antonio',\n", " 'Pierce',\n", " ',',\n", " 'alcançaram',\n", " 'a',\n", " 'linha',\n", " 'de',\n", " 'uma',\n", " 'jarda',\n", " '.',\n", " 'Maroney',\n", " 'avançou',\n", " 'pelo',\n", " 'chão',\n", " 'e',\n", " 'anotou',\n", " 'o',\n", " 'primeiro',\n", " 'touchdown',\n", " 'do',\n", " 'jogo',\n", " '.',\n", " '\\n\\n',\n", " 'Os',\n", " 'Giants',\n", " 'pareciam',\n", " 'rumo',\n", " 'à',\n", " 'virada',\n", " 'na',\n", " 'campanha',\n", " 'seguinte',\n", " '.',\n", " 'Manning',\n", " 'achou',\n", " 'Amani',\n", " 'Toomer',\n", " 'para',\n", " 'um',\n", " 'avanço',\n", " 'de',\n", " '38',\n", " 'jardas',\n", " ',',\n", " 'e',\n", " 'o',\n", " 'time',\n", " 'de',\n", " 'Nova',\n", " 'York',\n", " 'entrou',\n", " 'novamente',\n", " 'na',\n", " 'red',\n", " 'zone',\n", " '.',\n", " 'Com',\n", " 'a',\n", " 'bola',\n", " 'na',\n", " 'linha',\n", " 'de',\n", " '14',\n", " 'jardas',\n", " 'dos',\n", " 'Patriots',\n", " ',',\n", " 'os',\n", " 'Giants',\n", " 'sofreram',\n", " 'um',\n", " 'revés',\n", " '.',\n", " 'Manning',\n", " 'passou',\n", " 'para',\n", " 'Steve',\n", " 'Smith',\n", " ',',\n", " 'que',\n", " 'soltou',\n", " 'a',\n", " 'bola',\n", " '.',\n", " 'Ellis',\n", " 'Hobbs',\n", " 'aproveitou',\n", " ',',\n", " 'tomou',\n", " 'a',\n", " 'posse',\n", " 'para',\n", " 'os',\n", " 'Patriots',\n", " ',',\n", " 'e',\n", " 'avançou',\n", " '23',\n", " 'jardas',\n", " '.',\n", " '\\n\\n',\n", " 'A',\n", " 'defesa',\n", " 'de',\n", " 'Nova',\n", " 'York',\n", " 'manteve',\n", " 'o',\n", " 'jogo',\n", " 'equilibrado',\n", " '.',\n", " 'Com',\n", " 'dois',\n", " 'sacks',\n", " 'seguidos',\n", " ',',\n", " 'os',\n", " 'Giants',\n", " 'forçaram',\n", " 'o',\n", " 'punt',\n", " 'e',\n", " 'recuperaram',\n", " 'a',\n", " 'bola',\n", " '.',\n", " 'Mas',\n", " 'a',\n", " 'campanha',\n", " 'seguinte',\n", " 'provou',\n", " 'ser',\n", " 'outra',\n", " 'decepção',\n", " 'para',\n", " 'Nova',\n", " 'York',\n", " '.',\n", " 'O',\n", " 'time',\n", " 'chegou',\n", " 'à',\n", " 'linha',\n", " 'de',\n", " '25',\n", " 'jardas',\n", " ',',\n", " 'mas',\n", " 'Manning',\n", " 'sofreu',\n", " 'um',\n", " 'sack',\n", " 'e',\n", " 'cometeu',\n", " 'um',\n", " 'fumble',\n", " ',',\n", " 'e',\n", " 'o',\n", " 'ataque',\n", " 'voltou',\n", " 'para',\n", " 'a',\n", " 'linha',\n", " 'de',\n", " '39',\n", " 'jardas',\n", " ',',\n", " 'não',\n", " 'conseguindo',\n", " 'pontuar',\n", " 'mais',\n", " 'uma',\n", " 'vez',\n", " '.',\n", " '\\n\\n',\n", " 'Os',\n", " 'Patriots',\n", " 'tiveram',\n", " 'uma',\n", " 'última',\n", " 'chance',\n", " 'de',\n", " 'marcar',\n", " 'antes',\n", " 'do',\n", " 'intervalo',\n", " ',',\n", " 'mas',\n", " ',',\n", " 'a',\n", " '22',\n", " 'segundos',\n", " 'do',\n", " 'fim',\n", " 'do',\n", " 'segundo',\n", " 'período',\n", " ',',\n", " 'Brady',\n", " 'foi',\n", " 'novamente',\n", " 'sacado',\n", " '.',\n", " 'Desta',\n", " 'vez',\n", " ',',\n", " 'ele',\n", " 'cometeu',\n", " 'o',\n", " 'fumble',\n", " 'e',\n", " 'os',\n", " 'Giants',\n", " 'tomaram',\n", " 'a',\n", " 'posse',\n", " 'de',\n", " 'bola',\n", " '.',\n", " 'Manning',\n", " 'tentou',\n", " 'um',\n", " 'passe',\n", " 'longo',\n", " ',',\n", " 'de',\n", " '50',\n", " 'jardas',\n", " ',',\n", " 'nos',\n", " 'últimos',\n", " 'segundos',\n", " ',',\n", " 'mas',\n", " 'não',\n", " 'teve',\n", " 'sucesso',\n", " '.',\n", " '\\n\\n',\n", " 'O',\n", " 'jogo',\n", " 'continuou',\n", " 'amarrado',\n", " 'no',\n", " 'terceiro',\n", " 'quarto',\n", " ',',\n", " 'com',\n", " 'as',\n", " 'defesas',\n", " 'levando',\n", " 'a',\n", " 'melhor',\n", " 'sobre',\n", " 'os',\n", " 'ataques',\n", " '.',\n", " 'A',\n", " 'única',\n", " 'chance',\n", " 'de',\n", " 'pontuar',\n", " 'do',\n", " 'período',\n", " 'foi',\n", " 'dos',\n", " 'Patriots',\n", " ',',\n", " 'que',\n", " 'chegaram',\n", " 'à',\n", " 'linha',\n", " 'de',\n", " '31',\n", " 'jardas',\n", " 'dos',\n", " 'Giants',\n", " '.',\n", " 'O',\n", " 'técnico',\n", " 'Bill',\n", " 'Bellichick',\n", " ',',\n", " 'porém',\n", " ',',\n", " 'optou',\n", " 'por',\n", " 'uma',\n", " 'quarta',\n", " 'descida',\n", " 'em',\n", " 'vez',\n", " 'de',\n", " 'um',\n", " 'field',\n", " 'goal',\n", " '.',\n", " 'Brady',\n", " 'tentou',\n", " 'um',\n", " 'passe',\n", " 'para',\n", " 'Jabar',\n", " 'Gaffney',\n", " ',',\n", " 'mas',\n", " 'não',\n", " 'conseguiu',\n", " 'completar',\n", " '.',\n", " '\\n\\n',\n", " 'O',\n", " 'último',\n", " 'período',\n", " 'começou',\n", " 'arrasador',\n", " 'para',\n", " 'os',\n", " 'Giants',\n", " '.',\n", " 'na',\n", " 'primeira',\n", " 'jogada',\n", " ',',\n", " 'Manning',\n", " 'achou',\n", " 'o',\n", " 'tight',\n", " 'end',\n", " 'Kevin',\n", " 'Boss',\n", " ',',\n", " 'para',\n", " 'um',\n", " 'incrível',\n", " 'avanço',\n", " 'de',\n", " '45',\n", " 'jardas',\n", " ',',\n", " 'que',\n", " 'deixou',\n", " 'o',\n", " 'time',\n", " 'na',\n", " 'linha',\n", " 'de',\n", " '35',\n", " 'dos',\n", " 'Patriots',\n", " '.',\n", " 'Outro',\n", " 'lançamento',\n", " ',',\n", " 'desta',\n", " 'vez',\n", " 'para',\n", " 'Steve',\n", " 'Smith',\n", " ',',\n", " 'marcou',\n", " 'o',\n", " 'avanço',\n", " 'até',\n", " 'a',\n", " 'linha',\n", " 'de',\n", " '12',\n", " 'jardas',\n", " '.',\n", " 'Duas',\n", " 'jogadas',\n", " 'depois',\n", " ',',\n", " 'David',\n", " 'Tyree',\n", " 'pegou',\n", " 'um',\n", " 'passe',\n", " 'de',\n", " 'cinco',\n", " 'jardas',\n", " 'na',\n", " 'end',\n", " 'zone',\n", " 'para',\n", " 'anotar',\n", " 'o',\n", " 'touchdown',\n", " 'e',\n", " 'virar',\n", " 'o',\n", " 'jogo',\n", " '.',\n", " '\\n\\n',\n", " 'Na',\n", " 'hora',\n", " 'da',\n", " 'decisão',\n", " ',',\n", " 'o',\n", " 'ataque',\n", " 'dos',\n", " 'Patriots',\n", " 'voltou',\n", " 'a',\n", " 'funcionar',\n", " '.',\n", " 'Com',\n", " 'uma',\n", " 'série',\n", " 'de',\n", " 'passes',\n", " 'curtos',\n", " 'e',\n", " 'variados',\n", " ',',\n", " 'Brady',\n", " 'achou',\n", " 'Wes',\n", " 'Welker',\n", " ',',\n", " 'Randy',\n", " 'Moss',\n", " 'e',\n", " 'Kevin',\n", " 'Faulk',\n", " 'seguidas',\n", " 'vezes',\n", " 'até',\n", " 'chegar',\n", " 'à',\n", " 'red',\n", " 'zone',\n", " '.',\n", " 'A',\n", " '2m45s',\n", " 'do',\n", " 'fim',\n", " ',',\n", " 'o',\n", " 'quarterback',\n", " 'conectou',\n", " 'mais',\n", " 'uma',\n", " 'vez',\n", " 'com',\n", " 'Moss',\n", " ',',\n", " 'que',\n", " 'se',\n", " 'desmarcou',\n", " 'e',\n", " 'ficou',\n", " 'livre',\n", " 'na',\n", " 'lateral',\n", " 'direita',\n", " 'da',\n", " 'end',\n", " 'zone',\n", " '.',\n", " '\\n\\n',\n", " 'Quando',\n", " 'os',\n", " 'fãs',\n", " 'de',\n", " 'New',\n", " 'England',\n", " 'já',\n", " 'comemoravam',\n", " 'a',\n", " 'vitória',\n", " ',',\n", " 'o',\n", " 'inesperado',\n", " 'aconteceu',\n", " '.',\n", " 'Em',\n", " 'uma',\n", " 'jogada',\n", " 'incrível',\n", " ',',\n", " 'Eli',\n", " 'Manning',\n", " 'se',\n", " 'soltou',\n", " 'de',\n", " 'dois',\n", " 'marcadores',\n", " 'que',\n", " 'o',\n", " 'seguravam',\n", " 'pela',\n", " 'camisa',\n", " 'e',\n", " ',',\n", " 'na',\n", " 'corrida',\n", " ',',\n", " 'lançou',\n", " 'para',\n", " 'Amani',\n", " 'Toomer',\n", " '.',\n", " 'O',\n", " 'wide',\n", " 'receiver',\n", " ',',\n", " 'bem',\n", " 'marcado',\n", " ',',\n", " 'saltou',\n", " 'e',\n", " 'conseguiu',\n", " 'a',\n", " 'fazer',\n", " 'recepção',\n", " 'para',\n", " 'um',\n", " 'avanço',\n", " 'de',\n", " '32',\n", " 'jardas',\n", " ',',\n", " 'deixando',\n", " 'os',\n", " 'Giants',\n", " 'na',\n", " 'linha',\n", " 'de',\n", " '24',\n", " 'de',\n", " 'New',\n", " 'England',\n", " '.',\n", " '\\n\\n',\n", " 'Quatro',\n", " 'jogadas',\n", " 'depois',\n", " ',',\n", " 'a',\n", " '39',\n", " 'segundos',\n", " 'do',\n", " 'fim',\n", " ',',\n", " 'Manning',\n", " 'achou',\n", " 'Plaxico',\n", " 'Burress',\n", " 'na',\n", " 'end',\n", " 'zone',\n", " 'para',\n", " 'conseguir',\n", " 'o',\n", " 'touchdown',\n", " 'do',\n", " 'título',\n", " '.']" ] }, "metadata": {}, "execution_count": 18 } ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "m_cHef15OYBM", "outputId": "4b422fdc-bcbf-4864-d3db-6fee853d12bb" }, "source": [ "alpha_tokens = [token.orth_ for token in doc if token.is_alpha]\n", "print(\"Alpha Tokens: %s \" % (alpha_tokens))\n", "\n", "digit_tokens = [token.orth_ for token in doc if token.is_digit]\n", "print(\"Digit Tokens: %s \" % (digit_tokens))\n", "\n", "punct_tokens = [token.orth_ for token in doc if token.is_punct]\n", "print(\"Punct Tokens: %s \" % (punct_tokens))" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Alpha Tokens: ['Giants', 'batem', 'os', 'Patriots', 'no', 'Super', 'Bowl', 'XLII', 'Azarões', 'acabam', 'com', 'a', 'invencibilidade', 'de', 'New', 'England', 'e', 'ficam', 'com', 'o', 'título', 'da', 'temporada', 'm', 'Atualizado', 'em', 'm', 'Com', 'um', 'passe', 'de', 'Eli', 'Manning', 'para', 'Plaxico', 'Burress', 'a', 'segundos', 'do', 'fim', 'o', 'New', 'York', 'Giants', 'anotou', 'o', 'touchdown', 'decisivo', 'e', 'derrubou', 'o', 'favorito', 'New', 'England', 'Patriots', 'por', 'a', 'neste', 'domingo', 'em', 'Glendale', 'no', 'Super', 'Bowl', 'XLII', 'O', 'resultado', 'uma', 'das', 'maiores', 'zebras', 'da', 'história', 'do', 'Super', 'Bowl', 'acabou', 'com', 'a', 'temporada', 'perfeita', 'de', 'Tom', 'Brady', 'e', 'companhia', 'que', 'esperavam', 'fazer', 'história', 'ao', 'levantar', 'o', 'troféu', 'da', 'NFL', 'sem', 'sofrer', 'uma', 'derrota', 'no', 'ano', 'A', 'vitória', 'dos', 'Giants', 'porém', 'também', 'ficará', 'para', 'a', 'história', 'Pela', 'primeira', 'vez', 'irmãos', 'quarterbacks', 'triunfam', 'no', 'Super', 'Bowl', 'em', 'temporadas', 'consecutivas', 'No', 'ano', 'passado', 'Peyton', 'Manning', 'irmão', 'de', 'Eli', 'chegou', 'ao', 'título', 'máximo', 'da', 'NFL', 'pelo', 'Indianapolis', 'Colts', 'A', 'partida', 'Os', 'Giants', 'começaram', 'com', 'a', 'posse', 'de', 'bola', 'e', 'mostraram', 'logo', 'que', 'iriam', 'alongar', 'ao', 'máximo', 'suas', 'posses', 'de', 'bola', 'Misturando', 'corridas', 'com', 'Brandon', 'Jacobs', 'e', 'passes', 'curtos', 'o', 'time', 'de', 'Nova', 'York', 'chegou', 'à', 'red', 'zone', 'logo', 'na', 'primeira', 'campanha', 'O', 'avanço', 'no', 'entanto', 'parou', 'na', 'linha', 'de', 'jardas', 'e', 'Lawrence', 'Tynes', 'converteu', 'o', 'field', 'goal', 'de', 'jardas', 'para', 'abrir', 'o', 'placar', 'Eli', 'Manning', 'e', 'companhia', 'ficaram', 'com', 'a', 'bola', 'mas', 'o', 'ataque', 'dos', 'Patriots', 'não', 'entrou', 'em', 'campo', 'frio', 'Logo', 'no', 'retorno', 'do', 'kickoff', 'o', 'running', 'back', 'Laurence', 'Maroney', 'avançou', 'jardas', 'deixando', 'Tom', 'Brady', 'em', 'boa', 'posição', 'Com', 'passes', 'curtos', 'os', 'Patriots', 'chegaram', 'à', 'linha', 'de', 'jardas', 'e', 'graças', 'a', 'uma', 'penalidade', 'interferência', 'de', 'passe', 'do', 'linebacker', 'Antonio', 'Pierce', 'alcançaram', 'a', 'linha', 'de', 'uma', 'jarda', 'Maroney', 'avançou', 'pelo', 'chão', 'e', 'anotou', 'o', 'primeiro', 'touchdown', 'do', 'jogo', 'Os', 'Giants', 'pareciam', 'rumo', 'à', 'virada', 'na', 'campanha', 'seguinte', 'Manning', 'achou', 'Amani', 'Toomer', 'para', 'um', 'avanço', 'de', 'jardas', 'e', 'o', 'time', 'de', 'Nova', 'York', 'entrou', 'novamente', 'na', 'red', 'zone', 'Com', 'a', 'bola', 'na', 'linha', 'de', 'jardas', 'dos', 'Patriots', 'os', 'Giants', 'sofreram', 'um', 'revés', 'Manning', 'passou', 'para', 'Steve', 'Smith', 'que', 'soltou', 'a', 'bola', 'Ellis', 'Hobbs', 'aproveitou', 'tomou', 'a', 'posse', 'para', 'os', 'Patriots', 'e', 'avançou', 'jardas', 'A', 'defesa', 'de', 'Nova', 'York', 'manteve', 'o', 'jogo', 'equilibrado', 'Com', 'dois', 'sacks', 'seguidos', 'os', 'Giants', 'forçaram', 'o', 'punt', 'e', 'recuperaram', 'a', 'bola', 'Mas', 'a', 'campanha', 'seguinte', 'provou', 'ser', 'outra', 'decepção', 'para', 'Nova', 'York', 'O', 'time', 'chegou', 'à', 'linha', 'de', 'jardas', 'mas', 'Manning', 'sofreu', 'um', 'sack', 'e', 'cometeu', 'um', 'fumble', 'e', 'o', 'ataque', 'voltou', 'para', 'a', 'linha', 'de', 'jardas', 'não', 'conseguindo', 'pontuar', 'mais', 'uma', 'vez', 'Os', 'Patriots', 'tiveram', 'uma', 'última', 'chance', 'de', 'marcar', 'antes', 'do', 'intervalo', 'mas', 'a', 'segundos', 'do', 'fim', 'do', 'segundo', 'período', 'Brady', 'foi', 'novamente', 'sacado', 'Desta', 'vez', 'ele', 'cometeu', 'o', 'fumble', 'e', 'os', 'Giants', 'tomaram', 'a', 'posse', 'de', 'bola', 'Manning', 'tentou', 'um', 'passe', 'longo', 'de', 'jardas', 'nos', 'últimos', 'segundos', 'mas', 'não', 'teve', 'sucesso', 'O', 'jogo', 'continuou', 'amarrado', 'no', 'terceiro', 'quarto', 'com', 'as', 'defesas', 'levando', 'a', 'melhor', 'sobre', 'os', 'ataques', 'A', 'única', 'chance', 'de', 'pontuar', 'do', 'período', 'foi', 'dos', 'Patriots', 'que', 'chegaram', 'à', 'linha', 'de', 'jardas', 'dos', 'Giants', 'O', 'técnico', 'Bill', 'Bellichick', 'porém', 'optou', 'por', 'uma', 'quarta', 'descida', 'em', 'vez', 'de', 'um', 'field', 'goal', 'Brady', 'tentou', 'um', 'passe', 'para', 'Jabar', 'Gaffney', 'mas', 'não', 'conseguiu', 'completar', 'O', 'último', 'período', 'começou', 'arrasador', 'para', 'os', 'Giants', 'na', 'primeira', 'jogada', 'Manning', 'achou', 'o', 'tight', 'end', 'Kevin', 'Boss', 'para', 'um', 'incrível', 'avanço', 'de', 'jardas', 'que', 'deixou', 'o', 'time', 'na', 'linha', 'de', 'dos', 'Patriots', 'Outro', 'lançamento', 'desta', 'vez', 'para', 'Steve', 'Smith', 'marcou', 'o', 'avanço', 'até', 'a', 'linha', 'de', 'jardas', 'Duas', 'jogadas', 'depois', 'David', 'Tyree', 'pegou', 'um', 'passe', 'de', 'cinco', 'jardas', 'na', 'end', 'zone', 'para', 'anotar', 'o', 'touchdown', 'e', 'virar', 'o', 'jogo', 'Na', 'hora', 'da', 'decisão', 'o', 'ataque', 'dos', 'Patriots', 'voltou', 'a', 'funcionar', 'Com', 'uma', 'série', 'de', 'passes', 'curtos', 'e', 'variados', 'Brady', 'achou', 'Wes', 'Welker', 'Randy', 'Moss', 'e', 'Kevin', 'Faulk', 'seguidas', 'vezes', 'até', 'chegar', 'à', 'red', 'zone', 'A', 'do', 'fim', 'o', 'quarterback', 'conectou', 'mais', 'uma', 'vez', 'com', 'Moss', 'que', 'se', 'desmarcou', 'e', 'ficou', 'livre', 'na', 'lateral', 'direita', 'da', 'end', 'zone', 'Quando', 'os', 'fãs', 'de', 'New', 'England', 'já', 'comemoravam', 'a', 'vitória', 'o', 'inesperado', 'aconteceu', 'Em', 'uma', 'jogada', 'incrível', 'Eli', 'Manning', 'se', 'soltou', 'de', 'dois', 'marcadores', 'que', 'o', 'seguravam', 'pela', 'camisa', 'e', 'na', 'corrida', 'lançou', 'para', 'Amani', 'Toomer', 'O', 'wide', 'receiver', 'bem', 'marcado', 'saltou', 'e', 'conseguiu', 'a', 'fazer', 'recepção', 'para', 'um', 'avanço', 'de', 'jardas', 'deixando', 'os', 'Giants', 'na', 'linha', 'de', 'de', 'New', 'England', 'Quatro', 'jogadas', 'depois', 'a', 'segundos', 'do', 'fim', 'Manning', 'achou', 'Plaxico', 'Burress', 'na', 'end', 'zone', 'para', 'conseguir', 'o', 'touchdown', 'do', 'título'] \n", "Digit Tokens: ['39', '17', '14', '17', '32', '43', '17', '38', '14', '23', '25', '39', '22', '50', '31', '45', '35', '12', '32', '24', '39'] \n", "Punct Tokens: ['-', '-', '-', ',', ',', ',', '.', ',', ',', ',', '.', ',', ',', '.', ',', '.', ',', ',', ',', '.', ',', '.', ',', '.', ',', ',', '.', ',', '.', ',', ',', '.', ',', ',', '(', ')', ',', '.', '.', '.', ',', '.', ',', '.', ',', '.', ',', ',', '.', '.', ',', '.', '.', ',', ',', ',', '.', ',', ',', ',', '.', ',', '.', ',', ',', ',', '.', ',', '.', ',', '.', ',', ',', '.', ',', '.', '.', ',', ',', ',', '.', ',', ',', '.', ',', '.', ',', '.', ',', ',', '.', ',', ',', '.', ',', '.', ',', ',', ',', '.', ',', ',', ',', '.', ',', ',', '.'] \n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "GhyxDky59k9m" }, "source": [ "**Lemmatização: *.lemma_***" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "DFlpqcyHOt-5", "outputId": "04a0436d-3012-45e6-e78c-9a9187df2165" }, "source": [ "lemmas = [token.lemma_ for token in doc if token.pos_ == 'VERB']\n", "lemmas" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "['bater',\n", " 'acabar',\n", " 'ficar',\n", " 'Atualizado',\n", " 'anotar',\n", " 'derrubar',\n", " 'acabar',\n", " 'esperar',\n", " 'fazer',\n", " 'levantar',\n", " 'sofrer',\n", " 'ficar',\n", " 'triunfar',\n", " 'chegar',\n", " 'começar',\n", " 'mostrar',\n", " 'alongar',\n", " 'Misturando',\n", " 'chegar',\n", " 'parar',\n", " 'converter',\n", " 'abrir',\n", " 'ficar',\n", " 'entrar',\n", " 'avançar',\n", " 'deixar',\n", " 'chegar',\n", " 'alcançar',\n", " 'avançar',\n", " 'anotar',\n", " 'parecer',\n", " 'achar',\n", " 'entrar',\n", " 'sofrer',\n", " 'passar',\n", " 'soltar',\n", " 'aproveitar',\n", " 'tomar',\n", " 'avançar',\n", " 'manter',\n", " 'seguir',\n", " 'forçar',\n", " 'recuperar',\n", " 'provar',\n", " 'chegar',\n", " 'sofrer',\n", " 'cometer',\n", " 'voltar',\n", " 'conseguir',\n", " 'pontuar',\n", " 'ter',\n", " 'marcar',\n", " 'sacar',\n", " 'cometer',\n", " 'tomar',\n", " 'tentar',\n", " 'ter',\n", " 'continuar',\n", " 'amarrar',\n", " 'levar',\n", " 'pontuar',\n", " 'chegar',\n", " 'optar',\n", " 'tentar',\n", " 'conseguir',\n", " 'completar',\n", " 'começar',\n", " 'achar',\n", " 'deixar',\n", " 'marcar',\n", " 'pegar',\n", " 'anotar',\n", " 'virar',\n", " 'voltar',\n", " 'funcionar',\n", " 'achar',\n", " 'seguir',\n", " 'chegar',\n", " 'conectar',\n", " 'desmarcar',\n", " 'ficar',\n", " 'comemorar',\n", " 'acontecer',\n", " 'soltar',\n", " 'segurar',\n", " 'lançar',\n", " 'marcar',\n", " 'saltar',\n", " 'conseguir',\n", " 'fazer',\n", " 'deixar',\n", " 'achar',\n", " 'conseguir']" ] }, "metadata": {}, "execution_count": 20 } ] }, { "cell_type": "markdown", "metadata": { "id": "lp7NrAUw9tWl" }, "source": [ "**Etiquetas morfosintáticas: *.pos_***" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "FJ6n-uiFP2DR", "outputId": "ed5fe2dc-7b7f-4911-e93e-0a5fc7e072a0" }, "source": [ "pos = [(token.orth_, token.pos_) for token in doc]\n", "pos" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "[('Giants', 'PROPN'),\n", " ('batem', 'VERB'),\n", " ('os', 'DET'),\n", " ('Patriots', 'PROPN'),\n", " ('no', 'ADP'),\n", " ('Super', 'PROPN'),\n", " ('Bowl', 'PROPN'),\n", " ('XLII', 'PROPN'),\n", " ('\\n', 'SPACE'),\n", " ('Azarões', 'PROPN'),\n", " ('acabam', 'VERB'),\n", " ('com', 'ADP'),\n", " ('a', 'DET'),\n", " ('invencibilidade', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('New', 'PROPN'),\n", " ('England', 'PROPN'),\n", " ('e', 'CCONJ'),\n", " ('ficam', 'VERB'),\n", " ('com', 'ADP'),\n", " ('o', 'DET'),\n", " ('título', 'NOUN'),\n", " ('da', 'ADP'),\n", " ('temporada', 'NOUN'),\n", " ('\\n', 'SPACE'),\n", " ('04/02/2008', 'NUM'),\n", " ('-', 'PUNCT'),\n", " ('01h07', 'NUM'),\n", " ('m', 'NUM'),\n", " ('-', 'PUNCT'),\n", " ('Atualizado', 'VERB'),\n", " ('em', 'ADP'),\n", " ('04/02/2008', 'NUM'),\n", " ('-', 'PUNCT'),\n", " ('09h49', 'NUM'),\n", " ('m', 'ADP'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Com', 'ADP'),\n", " ('um', 'DET'),\n", " ('passe', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('Eli', 'PROPN'),\n", " ('Manning', 'PROPN'),\n", " ('para', 'ADP'),\n", " ('Plaxico', 'PROPN'),\n", " ('Burress', 'PROPN'),\n", " ('a', 'ADP'),\n", " ('39', 'NUM'),\n", " ('segundos', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('fim', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('New', 'PROPN'),\n", " ('York', 'PROPN'),\n", " ('Giants', 'PROPN'),\n", " ('anotou', 'VERB'),\n", " ('o', 'DET'),\n", " ('touchdown', 'NOUN'),\n", " ('decisivo', 'ADJ'),\n", " ('e', 'CCONJ'),\n", " ('derrubou', 'VERB'),\n", " ('o', 'DET'),\n", " ('favorito', 'NOUN'),\n", " ('New', 'PROPN'),\n", " ('England', 'PROPN'),\n", " ('Patriots', 'PROPN'),\n", " ('por', 'ADP'),\n", " ('17', 'NUM'),\n", " ('a', 'ADP'),\n", " ('14', 'NUM'),\n", " ('neste', 'ADP'),\n", " ('domingo', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('em', 'ADP'),\n", " ('Glendale', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('no', 'ADP'),\n", " ('Super', 'PROPN'),\n", " ('Bowl', 'PROPN'),\n", " ('XLII', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('O', 'DET'),\n", " ('resultado', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('uma', 'NUM'),\n", " ('das', 'ADP'),\n", " ('maiores', 'ADJ'),\n", " ('zebras', 'NOUN'),\n", " ('da', 'ADP'),\n", " ('história', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('Super', 'PROPN'),\n", " ('Bowl', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('acabou', 'VERB'),\n", " ('com', 'ADP'),\n", " ('a', 'DET'),\n", " ('temporada', 'NOUN'),\n", " ('perfeita', 'ADJ'),\n", " ('de', 'ADP'),\n", " ('Tom', 'PROPN'),\n", " ('Brady', 'PROPN'),\n", " ('e', 'CCONJ'),\n", " ('companhia', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('que', 'PRON'),\n", " ('esperavam', 'VERB'),\n", " ('fazer', 'VERB'),\n", " ('história', 'NOUN'),\n", " ('ao', 'SCONJ'),\n", " ('levantar', 'VERB'),\n", " ('o', 'DET'),\n", " ('troféu', 'NOUN'),\n", " ('da', 'ADP'),\n", " ('NFL', 'PROPN'),\n", " ('sem', 'SCONJ'),\n", " ('sofrer', 'VERB'),\n", " ('uma', 'DET'),\n", " ('derrota', 'NOUN'),\n", " ('no', 'ADP'),\n", " ('ano', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('A', 'DET'),\n", " ('vitória', 'NOUN'),\n", " ('dos', 'ADP'),\n", " ('Giants', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('porém', 'CCONJ'),\n", " (',', 'PUNCT'),\n", " ('também', 'ADV'),\n", " ('ficará', 'VERB'),\n", " ('para', 'ADP'),\n", " ('a', 'DET'),\n", " ('história', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Pela', 'NOUN'),\n", " ('primeira', 'ADP'),\n", " ('vez', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('irmãos', 'NOUN'),\n", " ('quarterbacks', 'ADJ'),\n", " ('triunfam', 'VERB'),\n", " ('no', 'ADP'),\n", " ('Super', 'PROPN'),\n", " ('Bowl', 'PROPN'),\n", " ('em', 'ADP'),\n", " ('temporadas', 'NOUN'),\n", " ('consecutivas', 'ADJ'),\n", " ('.', 'PUNCT'),\n", " ('No', 'ADP'),\n", " ('ano', 'NOUN'),\n", " ('passado', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('Peyton', 'PROPN'),\n", " ('Manning', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('irmão', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('Eli', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('chegou', 'VERB'),\n", " ('ao', 'ADP'),\n", " ('título', 'NOUN'),\n", " ('máximo', 'ADJ'),\n", " ('da', 'ADP'),\n", " ('NFL', 'PROPN'),\n", " ('pelo', 'ADP'),\n", " ('Indianapolis', 'PROPN'),\n", " ('Colts', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('A', 'DET'),\n", " ('partida', 'NOUN'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('começaram', 'VERB'),\n", " ('com', 'ADP'),\n", " ('a', 'DET'),\n", " ('posse', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('bola', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('e', 'CCONJ'),\n", " ('mostraram', 'VERB'),\n", " ('logo', 'ADV'),\n", " ('que', 'SCONJ'),\n", " ('iriam', 'AUX'),\n", " ('alongar', 'VERB'),\n", " ('ao', 'ADP'),\n", " ('máximo', 'NOUN'),\n", " ('suas', 'DET'),\n", " ('posses', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('bola', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Misturando', 'VERB'),\n", " ('corridas', 'NOUN'),\n", " ('com', 'ADP'),\n", " ('Brandon', 'PROPN'),\n", " ('Jacobs', 'PROPN'),\n", " ('e', 'CCONJ'),\n", " ('passes', 'NOUN'),\n", " ('curtos', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('time', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('Nova', 'PROPN'),\n", " ('York', 'PROPN'),\n", " ('chegou', 'VERB'),\n", " ('à', 'ADP'),\n", " ('red', 'ADJ'),\n", " ('zone', 'NOUN'),\n", " ('logo', 'ADV'),\n", " ('na', 'ADP'),\n", " ('primeira', 'ADJ'),\n", " ('campanha', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('O', 'DET'),\n", " ('avanço', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('no', 'ADP'),\n", " ('entanto', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('parou', 'VERB'),\n", " ('na', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('17', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('Lawrence', 'PROPN'),\n", " ('Tynes', 'PROPN'),\n", " ('converteu', 'VERB'),\n", " ('o', 'DET'),\n", " ('field', 'NOUN'),\n", " ('goal', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('32', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('para', 'SCONJ'),\n", " ('abrir', 'VERB'),\n", " ('o', 'DET'),\n", " ('placar', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Eli', 'PROPN'),\n", " ('Manning', 'PROPN'),\n", " ('e', 'CCONJ'),\n", " ('companhia', 'NOUN'),\n", " ('ficaram', 'VERB'),\n", " ('9m54s', 'NUM'),\n", " ('com', 'ADP'),\n", " ('a', 'DET'),\n", " ('bola', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('mas', 'CCONJ'),\n", " ('o', 'DET'),\n", " ('ataque', 'NOUN'),\n", " ('dos', 'ADP'),\n", " ('Patriots', 'PROPN'),\n", " ('não', 'ADV'),\n", " ('entrou', 'VERB'),\n", " ('em', 'ADP'),\n", " ('campo', 'NOUN'),\n", " ('frio', 'ADJ'),\n", " ('.', 'PUNCT'),\n", " ('Logo', 'ADV'),\n", " ('no', 'ADP'),\n", " ('retorno', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('kickoff', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('running', 'NOUN'),\n", " ('back', 'PROPN'),\n", " ('Laurence', 'PROPN'),\n", " ('Maroney', 'PROPN'),\n", " ('avançou', 'VERB'),\n", " ('43', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('deixando', 'VERB'),\n", " ('Tom', 'PROPN'),\n", " ('Brady', 'PROPN'),\n", " ('em', 'ADP'),\n", " ('boa', 'ADJ'),\n", " ('posição', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Com', 'ADP'),\n", " ('passes', 'NOUN'),\n", " ('curtos', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('os', 'DET'),\n", " ('Patriots', 'PROPN'),\n", " ('chegaram', 'VERB'),\n", " ('à', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('17', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " (',', 'PUNCT'),\n", " ('graças', 'ADV'),\n", " ('a', 'ADP'),\n", " ('uma', 'DET'),\n", " ('penalidade', 'NOUN'),\n", " ('(', 'PUNCT'),\n", " ('interferência', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('passe', 'NOUN'),\n", " (')', 'PUNCT'),\n", " ('do', 'ADP'),\n", " ('linebacker', 'NOUN'),\n", " ('Antonio', 'PROPN'),\n", " ('Pierce', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('alcançaram', 'VERB'),\n", " ('a', 'DET'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('uma', 'DET'),\n", " ('jarda', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Maroney', 'PROPN'),\n", " ('avançou', 'VERB'),\n", " ('pelo', 'ADP'),\n", " ('chão', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('anotou', 'VERB'),\n", " ('o', 'DET'),\n", " ('primeiro', 'ADJ'),\n", " ('touchdown', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('jogo', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('pareciam', 'VERB'),\n", " ('rumo', 'ADV'),\n", " ('à', 'ADP'),\n", " ('virada', 'NOUN'),\n", " ('na', 'ADP'),\n", " ('campanha', 'NOUN'),\n", " ('seguinte', 'ADJ'),\n", " ('.', 'PUNCT'),\n", " ('Manning', 'PROPN'),\n", " ('achou', 'VERB'),\n", " ('Amani', 'PROPN'),\n", " ('Toomer', 'PROPN'),\n", " ('para', 'ADP'),\n", " ('um', 'DET'),\n", " ('avanço', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('38', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('e', 'CCONJ'),\n", " ('o', 'DET'),\n", " ('time', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('Nova', 'PROPN'),\n", " ('York', 'PROPN'),\n", " ('entrou', 'VERB'),\n", " ('novamente', 'ADV'),\n", " ('na', 'ADP'),\n", " ('red', 'ADJ'),\n", " ('zone', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Com', 'ADP'),\n", " ('a', 'DET'),\n", " ('bola', 'NOUN'),\n", " ('na', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('14', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('dos', 'ADP'),\n", " ('Patriots', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('sofreram', 'VERB'),\n", " ('um', 'DET'),\n", " ('revés', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Manning', 'PROPN'),\n", " ('passou', 'VERB'),\n", " ('para', 'ADP'),\n", " ('Steve', 'PROPN'),\n", " ('Smith', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('que', 'PRON'),\n", " ('soltou', 'VERB'),\n", " ('a', 'DET'),\n", " ('bola', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Ellis', 'PROPN'),\n", " ('Hobbs', 'PROPN'),\n", " ('aproveitou', 'VERB'),\n", " (',', 'PUNCT'),\n", " ('tomou', 'VERB'),\n", " ('a', 'DET'),\n", " ('posse', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('os', 'DET'),\n", " ('Patriots', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('e', 'CCONJ'),\n", " ('avançou', 'VERB'),\n", " ('23', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('A', 'DET'),\n", " ('defesa', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('Nova', 'PROPN'),\n", " ('York', 'PROPN'),\n", " ('manteve', 'VERB'),\n", " ('o', 'DET'),\n", " ('jogo', 'NOUN'),\n", " ('equilibrado', 'ADJ'),\n", " ('.', 'PUNCT'),\n", " ('Com', 'ADP'),\n", " ('dois', 'NUM'),\n", " ('sacks', 'NOUN'),\n", " ('seguidos', 'VERB'),\n", " (',', 'PUNCT'),\n", " ('os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('forçaram', 'VERB'),\n", " ('o', 'DET'),\n", " ('punt', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('recuperaram', 'VERB'),\n", " ('a', 'DET'),\n", " ('bola', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Mas', 'CCONJ'),\n", " ('a', 'DET'),\n", " ('campanha', 'NOUN'),\n", " ('seguinte', 'ADJ'),\n", " ('provou', 'VERB'),\n", " ('ser', 'AUX'),\n", " ('outra', 'DET'),\n", " ('decepção', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('Nova', 'PROPN'),\n", " ('York', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('O', 'DET'),\n", " ('time', 'NOUN'),\n", " ('chegou', 'VERB'),\n", " ('à', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('25', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('mas', 'CCONJ'),\n", " ('Manning', 'PROPN'),\n", " ('sofreu', 'VERB'),\n", " ('um', 'DET'),\n", " ('sack', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('cometeu', 'VERB'),\n", " ('um', 'DET'),\n", " ('fumble', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('e', 'CCONJ'),\n", " ('o', 'DET'),\n", " ('ataque', 'NOUN'),\n", " ('voltou', 'VERB'),\n", " ('para', 'ADP'),\n", " ('a', 'DET'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('39', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('não', 'ADV'),\n", " ('conseguindo', 'VERB'),\n", " ('pontuar', 'VERB'),\n", " ('mais', 'ADV'),\n", " ('uma', 'ADP'),\n", " ('vez', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Os', 'DET'),\n", " ('Patriots', 'PROPN'),\n", " ('tiveram', 'VERB'),\n", " ('uma', 'DET'),\n", " ('última', 'ADJ'),\n", " ('chance', 'NOUN'),\n", " ('de', 'SCONJ'),\n", " ('marcar', 'VERB'),\n", " ('antes', 'ADV'),\n", " ('do', 'ADP'),\n", " ('intervalo', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('mas', 'CCONJ'),\n", " (',', 'PUNCT'),\n", " ('a', 'ADP'),\n", " ('22', 'NUM'),\n", " ('segundos', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('fim', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('segundo', 'ADJ'),\n", " ('período', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('Brady', 'PROPN'),\n", " ('foi', 'AUX'),\n", " ('novamente', 'ADV'),\n", " ('sacado', 'VERB'),\n", " ('.', 'PUNCT'),\n", " ('Desta', 'ADP'),\n", " ('vez', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('ele', 'PRON'),\n", " ('cometeu', 'VERB'),\n", " ('o', 'DET'),\n", " ('fumble', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('tomaram', 'VERB'),\n", " ('a', 'DET'),\n", " ('posse', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('bola', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Manning', 'PROPN'),\n", " ('tentou', 'VERB'),\n", " ('um', 'DET'),\n", " ('passe', 'NOUN'),\n", " ('longo', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('de', 'ADP'),\n", " ('50', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('nos', 'ADP'),\n", " ('últimos', 'ADJ'),\n", " ('segundos', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('mas', 'CCONJ'),\n", " ('não', 'ADV'),\n", " ('teve', 'VERB'),\n", " ('sucesso', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('O', 'DET'),\n", " ('jogo', 'NOUN'),\n", " ('continuou', 'VERB'),\n", " ('amarrado', 'VERB'),\n", " ('no', 'ADP'),\n", " ('terceiro', 'ADJ'),\n", " ('quarto', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('com', 'ADP'),\n", " ('as', 'DET'),\n", " ('defesas', 'NOUN'),\n", " ('levando', 'VERB'),\n", " ('a', 'DET'),\n", " ('melhor', 'ADV'),\n", " ('sobre', 'ADP'),\n", " ('os', 'DET'),\n", " ('ataques', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('A', 'DET'),\n", " ('única', 'ADJ'),\n", " ('chance', 'NOUN'),\n", " ('de', 'SCONJ'),\n", " ('pontuar', 'VERB'),\n", " ('do', 'ADP'),\n", " ('período', 'NOUN'),\n", " ('foi', 'AUX'),\n", " ('dos', 'ADP'),\n", " ('Patriots', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('que', 'PRON'),\n", " ('chegaram', 'VERB'),\n", " ('à', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('31', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('dos', 'ADP'),\n", " ('Giants', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('O', 'DET'),\n", " ('técnico', 'NOUN'),\n", " ('Bill', 'PROPN'),\n", " ('Bellichick', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('porém', 'CCONJ'),\n", " (',', 'PUNCT'),\n", " ('optou', 'VERB'),\n", " ('por', 'ADP'),\n", " ('uma', 'DET'),\n", " ('quarta', 'ADJ'),\n", " ('descida', 'NOUN'),\n", " ('em', 'ADP'),\n", " ('vez', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('um', 'DET'),\n", " ('field', 'NOUN'),\n", " ('goal', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('Brady', 'PROPN'),\n", " ('tentou', 'VERB'),\n", " ('um', 'DET'),\n", " ('passe', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('Jabar', 'PROPN'),\n", " ('Gaffney', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('mas', 'CCONJ'),\n", " ('não', 'ADV'),\n", " ('conseguiu', 'VERB'),\n", " ('completar', 'VERB'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('O', 'DET'),\n", " ('último', 'ADJ'),\n", " ('período', 'NOUN'),\n", " ('começou', 'VERB'),\n", " ('arrasador', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('na', 'ADP'),\n", " ('primeira', 'ADJ'),\n", " ('jogada', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('Manning', 'PROPN'),\n", " ('achou', 'VERB'),\n", " ('o', 'DET'),\n", " ('tight', 'NOUN'),\n", " ('end', 'X'),\n", " ('Kevin', 'PROPN'),\n", " ('Boss', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('para', 'ADP'),\n", " ('um', 'DET'),\n", " ('incrível', 'ADJ'),\n", " ('avanço', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('45', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('que', 'PRON'),\n", " ('deixou', 'VERB'),\n", " ('o', 'DET'),\n", " ('time', 'NOUN'),\n", " ('na', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('35', 'NUM'),\n", " ('dos', 'ADP'),\n", " ('Patriots', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('Outro', 'DET'),\n", " ('lançamento', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('desta', 'ADP'),\n", " ('vez', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('Steve', 'PROPN'),\n", " ('Smith', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('marcou', 'VERB'),\n", " ('o', 'DET'),\n", " ('avanço', 'NOUN'),\n", " ('até', 'ADP'),\n", " ('a', 'DET'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('12', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('Duas', 'NUM'),\n", " ('jogadas', 'NOUN'),\n", " ('depois', 'ADV'),\n", " (',', 'PUNCT'),\n", " ('David', 'PROPN'),\n", " ('Tyree', 'PROPN'),\n", " ('pegou', 'VERB'),\n", " ('um', 'DET'),\n", " ('passe', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('cinco', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " ('na', 'ADP'),\n", " ('end', 'X'),\n", " ('zone', 'X'),\n", " ('para', 'SCONJ'),\n", " ('anotar', 'VERB'),\n", " ('o', 'DET'),\n", " ('touchdown', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " ('virar', 'VERB'),\n", " ('o', 'DET'),\n", " ('jogo', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Na', 'ADP'),\n", " ('hora', 'NOUN'),\n", " ('da', 'ADP'),\n", " ('decisão', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('ataque', 'NOUN'),\n", " ('dos', 'ADP'),\n", " ('Patriots', 'PROPN'),\n", " ('voltou', 'VERB'),\n", " ('a', 'SCONJ'),\n", " ('funcionar', 'VERB'),\n", " ('.', 'PUNCT'),\n", " ('Com', 'ADP'),\n", " ('uma', 'DET'),\n", " ('série', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('passes', 'NOUN'),\n", " ('curtos', 'ADJ'),\n", " ('e', 'CCONJ'),\n", " ('variados', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('Brady', 'PROPN'),\n", " ('achou', 'VERB'),\n", " ('Wes', 'PROPN'),\n", " ('Welker', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('Randy', 'PROPN'),\n", " ('Moss', 'PROPN'),\n", " ('e', 'CCONJ'),\n", " ('Kevin', 'PROPN'),\n", " ('Faulk', 'PROPN'),\n", " ('seguidas', 'VERB'),\n", " ('vezes', 'NOUN'),\n", " ('até', 'ADV'),\n", " ('chegar', 'VERB'),\n", " ('à', 'ADP'),\n", " ('red', 'ADJ'),\n", " ('zone', 'NOUN'),\n", " ('.', 'PUNCT'),\n", " ('A', 'DET'),\n", " ('2m45s', 'PROPN'),\n", " ('do', 'ADP'),\n", " ('fim', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('quarterback', 'NOUN'),\n", " ('conectou', 'VERB'),\n", " ('mais', 'ADV'),\n", " ('uma', 'ADP'),\n", " ('vez', 'NOUN'),\n", " ('com', 'ADP'),\n", " ('Moss', 'PROPN'),\n", " (',', 'PUNCT'),\n", " ('que', 'PRON'),\n", " ('se', 'PRON'),\n", " ('desmarcou', 'VERB'),\n", " ('e', 'CCONJ'),\n", " ('ficou', 'VERB'),\n", " ('livre', 'ADJ'),\n", " ('na', 'ADP'),\n", " ('lateral', 'NOUN'),\n", " ('direita', 'ADJ'),\n", " ('da', 'ADP'),\n", " ('end', 'X'),\n", " ('zone', 'X'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Quando', 'SCONJ'),\n", " ('os', 'DET'),\n", " ('fãs', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('New', 'PROPN'),\n", " ('England', 'PROPN'),\n", " ('já', 'ADV'),\n", " ('comemoravam', 'VERB'),\n", " ('a', 'DET'),\n", " ('vitória', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('o', 'DET'),\n", " ('inesperado', 'NOUN'),\n", " ('aconteceu', 'VERB'),\n", " ('.', 'PUNCT'),\n", " ('Em', 'ADP'),\n", " ('uma', 'DET'),\n", " ('jogada', 'NOUN'),\n", " ('incrível', 'ADJ'),\n", " (',', 'PUNCT'),\n", " ('Eli', 'PROPN'),\n", " ('Manning', 'PROPN'),\n", " ('se', 'PRON'),\n", " ('soltou', 'VERB'),\n", " ('de', 'ADP'),\n", " ('dois', 'NUM'),\n", " ('marcadores', 'NOUN'),\n", " ('que', 'PRON'),\n", " ('o', 'PRON'),\n", " ('seguravam', 'VERB'),\n", " ('pela', 'ADP'),\n", " ('camisa', 'NOUN'),\n", " ('e', 'CCONJ'),\n", " (',', 'PUNCT'),\n", " ('na', 'ADP'),\n", " ('corrida', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('lançou', 'VERB'),\n", " ('para', 'ADP'),\n", " ('Amani', 'PROPN'),\n", " ('Toomer', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('O', 'DET'),\n", " ('wide', 'NOUN'),\n", " ('receiver', 'X'),\n", " (',', 'PUNCT'),\n", " ('bem', 'ADV'),\n", " ('marcado', 'VERB'),\n", " (',', 'PUNCT'),\n", " ('saltou', 'VERB'),\n", " ('e', 'CCONJ'),\n", " ('conseguiu', 'VERB'),\n", " ('a', 'SCONJ'),\n", " ('fazer', 'VERB'),\n", " ('recepção', 'NOUN'),\n", " ('para', 'ADP'),\n", " ('um', 'DET'),\n", " ('avanço', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('32', 'NUM'),\n", " ('jardas', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('deixando', 'VERB'),\n", " ('os', 'DET'),\n", " ('Giants', 'PROPN'),\n", " ('na', 'ADP'),\n", " ('linha', 'NOUN'),\n", " ('de', 'ADP'),\n", " ('24', 'NUM'),\n", " ('de', 'ADP'),\n", " ('New', 'PROPN'),\n", " ('England', 'PROPN'),\n", " ('.', 'PUNCT'),\n", " ('\\n\\n', 'SPACE'),\n", " ('Quatro', 'NUM'),\n", " ('jogadas', 'NOUN'),\n", " ('depois', 'ADV'),\n", " (',', 'PUNCT'),\n", " ('a', 'ADP'),\n", " ('39', 'NUM'),\n", " ('segundos', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('fim', 'NOUN'),\n", " (',', 'PUNCT'),\n", " ('Manning', 'PROPN'),\n", " ('achou', 'VERB'),\n", " ('Plaxico', 'PROPN'),\n", " ('Burress', 'PROPN'),\n", " ('na', 'ADP'),\n", " ('end', 'PROPN'),\n", " ('zone', 'X'),\n", " ('para', 'SCONJ'),\n", " ('conseguir', 'VERB'),\n", " ('o', 'DET'),\n", " ('touchdown', 'NOUN'),\n", " ('do', 'ADP'),\n", " ('título', 'NOUN'),\n", " ('.', 'PUNCT')]" ] }, "metadata": {}, "execution_count": 22 } ] }, { "cell_type": "markdown", "metadata": { "id": "SyQrAvKo92a3" }, "source": [ "**Análise morfosintática: *.morph***" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Zq_mdqZyQW-f", "outputId": "8489031d-9b77-4318-b0d3-2052c4abc373" }, "source": [ "morfologicas = [(token.orth_, token.morph) for token in doc]\n", "morfologicas" ], "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "[('Giants', Gender=Masc|Number=Sing),\n", " ('batem', Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('Super', Gender=Masc|Number=Sing),\n", " ('Bowl', Number=Sing),\n", " ('XLII', Number=Sing),\n", " ('\\n', ),\n", " ('Azarões', Number=Sing),\n", " ('acabam', Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin),\n", " ('com', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('invencibilidade', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('New', Gender=Masc|Number=Sing),\n", " ('England', Number=Sing),\n", " ('e', ),\n", " ('ficam', Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin),\n", " ('com', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('título', Gender=Masc|Number=Sing),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('temporada', Gender=Fem|Number=Sing),\n", " ('\\n', ),\n", " ('04/02/2008', NumType=Card),\n", " ('-', ),\n", " ('01h07', NumType=Card),\n", " ('m', NumType=Card),\n", " ('-', ),\n", " ('Atualizado', Gender=Masc|Number=Sing|VerbForm=Part),\n", " ('em', ),\n", " ('04/02/2008', NumType=Card),\n", " ('-', ),\n", " ('09h49', NumType=Card),\n", " ('m', ),\n", " ('\\n\\n', ),\n", " ('Com', ),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('passe', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('Eli', Gender=Masc|Number=Sing),\n", " ('Manning', Number=Sing),\n", " ('para', ),\n", " ('Plaxico', Gender=Masc|Number=Sing),\n", " ('Burress', Number=Sing),\n", " ('a', ),\n", " ('39', NumType=Card),\n", " ('segundos', Gender=Masc|Number=Plur),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fim', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('New', Gender=Masc|Number=Sing),\n", " ('York', Number=Sing),\n", " ('Giants', Number=Sing),\n", " ('anotou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('touchdown', Gender=Masc|Number=Sing),\n", " ('decisivo', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('derrubou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('favorito', Gender=Masc|Number=Sing),\n", " ('New', Gender=Masc|Number=Sing),\n", " ('England', Number=Sing),\n", " ('Patriots', Number=Sing),\n", " ('por', ),\n", " ('17', NumType=Card),\n", " ('a', ),\n", " ('14', NumType=Card),\n", " ('neste', Gender=Masc|Number=Sing|PronType=Dem),\n", " ('domingo', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('em', ),\n", " ('Glendale', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('Super', Gender=Masc|Number=Sing),\n", " ('Bowl', Number=Sing),\n", " ('XLII', Number=Sing),\n", " ('.', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('resultado', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('uma', NumType=Card),\n", " ('das', Definite=Def|Gender=Fem|Number=Plur|PronType=Art),\n", " ('maiores', Gender=Fem|Number=Plur),\n", " ('zebras', Gender=Fem|Number=Plur),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('história', Gender=Fem|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('Super', Gender=Masc|Number=Sing),\n", " ('Bowl', Number=Sing),\n", " (',', ),\n", " ('acabou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('com', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('temporada', Gender=Fem|Number=Sing),\n", " ('perfeita', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('Tom', Gender=Masc|Number=Sing),\n", " ('Brady', Number=Sing),\n", " ('e', ),\n", " ('companhia', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('que', Gender=Fem|Number=Sing|PronType=Rel),\n", " ('esperavam', Mood=Ind|Number=Plur|Person=3|Tense=Imp|VerbForm=Fin),\n", " ('fazer', VerbForm=Inf),\n", " ('história', Gender=Fem|Number=Sing),\n", " ('ao', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('levantar', VerbForm=Inf),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('troféu', Gender=Masc|Number=Sing),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('NFL', Gender=Fem|Number=Sing),\n", " ('sem', ),\n", " ('sofrer', VerbForm=Inf),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('derrota', Gender=Fem|Number=Sing),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('ano', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('A', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('vitória', Gender=Fem|Number=Sing),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('porém', ),\n", " (',', ),\n", " ('também', ),\n", " ('ficará', Mood=Ind|Number=Sing|Person=3|Tense=Fut|VerbForm=Fin),\n", " ('para', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('história', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Pela', Gender=Masc|Number=Sing),\n", " ('primeira', ),\n", " ('vez', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('irmãos', Gender=Masc|Number=Plur),\n", " ('quarterbacks', Gender=Masc|Number=Plur),\n", " ('triunfam', Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('Super', Gender=Masc|Number=Sing),\n", " ('Bowl', Number=Sing),\n", " ('em', ),\n", " ('temporadas', Gender=Fem|Number=Plur),\n", " ('consecutivas', Gender=Fem|Number=Plur),\n", " ('.', ),\n", " ('No', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('ano', Gender=Masc|Number=Sing),\n", " ('passado', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('Peyton', Gender=Masc|Number=Sing),\n", " ('Manning', Number=Sing),\n", " (',', ),\n", " ('irmão', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('Eli', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('chegou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('ao', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('título', Gender=Masc|Number=Sing),\n", " ('máximo', Gender=Masc|Number=Sing),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('NFL', Gender=Fem|Number=Sing),\n", " ('pelo', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('Indianapolis', Gender=Masc|Number=Sing),\n", " ('Colts', Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('A', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('partida', Gender=Fem|Number=Sing),\n", " ('\\n\\n', ),\n", " ('Os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('começaram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('com', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('posse', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('bola', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('e', ),\n", " ('mostraram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('logo', ),\n", " ('que', ),\n", " ('iriam', Mood=Cnd|Number=Plur|Person=3|VerbForm=Fin),\n", " ('alongar', VerbForm=Inf),\n", " ('ao', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('máximo', Gender=Masc|Number=Sing),\n", " ('suas', Gender=Fem|Number=Plur|PronType=Prs),\n", " ('posses', Gender=Fem|Number=Plur),\n", " ('de', ),\n", " ('bola', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Misturando', VerbForm=Ger),\n", " ('corridas', Gender=Fem|Number=Plur),\n", " ('com', ),\n", " ('Brandon', Gender=Masc|Number=Sing),\n", " ('Jacobs', Number=Sing),\n", " ('e', ),\n", " ('passes', Gender=Masc|Number=Plur),\n", " ('curtos', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('time', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('Nova', Gender=Fem|Number=Sing),\n", " ('York', Number=Sing),\n", " ('chegou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('red', Gender=Masc|Number=Sing),\n", " ('zone', Gender=Masc|Number=Sing),\n", " ('logo', ),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('primeira', Gender=Fem|NumType=Ord|Number=Sing),\n", " ('campanha', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('avanço', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('entanto', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('parou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('17', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('e', ),\n", " ('Lawrence', Gender=Masc|Number=Sing),\n", " ('Tynes', Number=Sing),\n", " ('converteu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('field', Gender=Masc|Number=Sing),\n", " ('goal', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('32', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('para', ),\n", " ('abrir', VerbForm=Inf),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('placar', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Eli', Gender=Masc|Number=Sing),\n", " ('Manning', Number=Sing),\n", " ('e', ),\n", " ('companhia', Gender=Fem|Number=Sing),\n", " ('ficaram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('9m54s', NumType=Card),\n", " ('com', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('bola', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('mas', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('ataque', Gender=Masc|Number=Sing),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " ('não', Polarity=Neg),\n", " ('entrou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('em', ),\n", " ('campo', Gender=Masc|Number=Sing),\n", " ('frio', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('Logo', ),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('retorno', Gender=Masc|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('kickoff', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('running', Gender=Masc|Number=Sing),\n", " ('back', Number=Sing),\n", " ('Laurence', Gender=Masc|Number=Sing),\n", " ('Maroney', Number=Sing),\n", " ('avançou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('43', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('deixando', VerbForm=Ger),\n", " ('Tom', Gender=Masc|Number=Sing),\n", " ('Brady', Number=Sing),\n", " ('em', ),\n", " ('boa', Gender=Fem|Number=Sing),\n", " ('posição', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Com', ),\n", " ('passes', Gender=Masc|Number=Plur),\n", " ('curtos', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " ('chegaram', Mood=Ind|Number=Plur|Person=3|VerbForm=Fin),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('17', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('e', ),\n", " (',', ),\n", " ('graças', ),\n", " ('a', ),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('penalidade', Gender=Fem|Number=Sing),\n", " ('(', ),\n", " ('interferência', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('passe', Gender=Masc|Number=Sing),\n", " (')', ),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('linebacker', Gender=Masc|Number=Sing),\n", " ('Antonio', Gender=Masc|Number=Sing),\n", " ('Pierce', Number=Sing),\n", " (',', ),\n", " ('alcançaram', Mood=Ind|Number=Plur|Person=3|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('jarda', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Maroney', Gender=Masc|Number=Sing),\n", " ('avançou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('pelo', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('chão', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('anotou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('primeiro', Gender=Masc|NumType=Ord|Number=Sing),\n", " ('touchdown', Gender=Masc|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('jogo', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('pareciam', Mood=Ind|Number=Plur|Person=3|Tense=Imp|VerbForm=Fin),\n", " ('rumo', ),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('virada', Gender=Fem|Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('campanha', Gender=Fem|Number=Sing),\n", " ('seguinte', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('achou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('Amani', Gender=Masc|Number=Sing),\n", " ('Toomer', Number=Sing),\n", " ('para', ),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('avanço', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('38', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('e', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('time', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('Nova', Gender=Fem|Number=Sing),\n", " ('York', Number=Sing),\n", " ('entrou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('novamente', ),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('red', Gender=Masc|Number=Sing),\n", " ('zone', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('Com', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('bola', Gender=Fem|Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('14', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('sofreram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('revés', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('passou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('para', ),\n", " ('Steve', Gender=Masc|Number=Sing),\n", " ('Smith', Number=Sing),\n", " (',', ),\n", " ('que', Gender=Masc|Number=Sing|PronType=Rel),\n", " ('soltou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('bola', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Ellis', Gender=Masc|Number=Sing),\n", " ('Hobbs', Number=Sing),\n", " ('aproveitou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " (',', ),\n", " ('tomou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('posse', Gender=Fem|Number=Sing),\n", " ('para', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('e', ),\n", " ('avançou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('23', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('A', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('defesa', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('Nova', Gender=Fem|Number=Sing),\n", " ('York', Number=Sing),\n", " ('manteve', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('jogo', Gender=Masc|Number=Sing),\n", " ('equilibrado', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('Com', ),\n", " ('dois', NumType=Card),\n", " ('sacks', Gender=Masc|Number=Plur),\n", " ('seguidos', Gender=Masc|Number=Plur|VerbForm=Part),\n", " (',', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('forçaram', Mood=Ind|Number=Plur|Person=3|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('punt', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('recuperaram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('bola', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Mas', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('campanha', Gender=Fem|Number=Sing),\n", " ('seguinte', Gender=Fem|Number=Sing),\n", " ('provou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('ser', VerbForm=Inf),\n", " ('outra', Gender=Fem|Number=Sing|PronType=Ind),\n", " ('decepção', Gender=Fem|Number=Sing),\n", " ('para', ),\n", " ('Nova', Gender=Fem|Number=Sing),\n", " ('York', Number=Sing),\n", " ('.', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('time', Gender=Masc|Number=Sing),\n", " ('chegou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('25', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('mas', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('sofreu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('sack', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('cometeu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fumble', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('e', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('ataque', Gender=Masc|Number=Sing),\n", " ('voltou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('para', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('39', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('não', Polarity=Neg),\n", " ('conseguindo', VerbForm=Ger),\n", " ('pontuar', VerbForm=Inf),\n", " ('mais', ),\n", " ('uma', ),\n", " ('vez', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " ('tiveram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('última', Gender=Fem|NumType=Ord|Number=Sing),\n", " ('chance', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('marcar', VerbForm=Inf),\n", " ('antes', ),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('intervalo', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('mas', ),\n", " (',', ),\n", " ('a', ),\n", " ('22', NumType=Card),\n", " ('segundos', Gender=Masc|Number=Plur),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fim', Gender=Masc|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('segundo', Gender=Masc|NumType=Ord|Number=Sing),\n", " ('período', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('Brady', Gender=Masc|Number=Sing),\n", " ('foi', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('novamente', ),\n", " ('sacado', Gender=Masc|Number=Sing|VerbForm=Part),\n", " ('.', ),\n", " ('Desta', ),\n", " ('vez', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('ele', Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs),\n", " ('cometeu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fumble', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('tomaram', Mood=Ind|Number=Plur|Person=3|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('posse', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('bola', Gender=Fem|Number=Sing),\n", " ('.', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('tentou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('passe', Gender=Masc|Number=Sing),\n", " ('longo', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('de', ),\n", " ('50', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('nos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('últimos', Gender=Masc|NumType=Ord|Number=Plur),\n", " ('segundos', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('mas', ),\n", " ('não', Polarity=Neg),\n", " ('teve', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('sucesso', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('jogo', Gender=Masc|Number=Sing),\n", " ('continuou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('amarrado', Gender=Masc|Number=Sing|VerbForm=Part),\n", " ('no', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('terceiro', Gender=Masc|NumType=Ord|Number=Sing),\n", " ('quarto', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('com', ),\n", " ('as', Definite=Def|Gender=Fem|Number=Plur|PronType=Art),\n", " ('defesas', Gender=Fem|Number=Plur),\n", " ('levando', VerbForm=Ger),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('melhor', ),\n", " ('sobre', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('ataques', Gender=Masc|Number=Plur),\n", " ('.', ),\n", " ('A', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('única', Gender=Fem|Number=Sing),\n", " ('chance', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('pontuar', VerbForm=Inf),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('período', Gender=Masc|Number=Sing),\n", " ('foi', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('que', Gender=Masc|Number=Plur|PronType=Rel),\n", " ('chegaram', Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('31', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('técnico', Gender=Masc|Number=Sing),\n", " ('Bill', Gender=Masc|Number=Sing),\n", " ('Bellichick', Number=Sing),\n", " (',', ),\n", " ('porém', ),\n", " (',', ),\n", " ('optou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('por', ),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('quarta', Gender=Fem|NumType=Ord|Number=Sing),\n", " ('descida', Gender=Fem|Number=Sing),\n", " ('em', ),\n", " ('vez', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('field', Gender=Masc|Number=Sing),\n", " ('goal', Number=Sing),\n", " ('.', ),\n", " ('Brady', Gender=Masc|Number=Sing),\n", " ('tentou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('passe', Gender=Masc|Number=Sing),\n", " ('para', ),\n", " ('Jabar', Gender=Masc|Number=Sing),\n", " ('Gaffney', Number=Sing),\n", " (',', ),\n", " ('mas', ),\n", " ('não', Polarity=Neg),\n", " ('conseguiu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('completar', VerbForm=Inf),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('último', Gender=Masc|NumType=Ord|Number=Sing),\n", " ('período', Gender=Masc|Number=Sing),\n", " ('começou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('arrasador', Gender=Masc|Number=Sing),\n", " ('para', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Plur),\n", " ('.', ),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('primeira', Gender=Fem|NumType=Ord|Number=Sing),\n", " ('jogada', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('achou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('tight', Gender=Masc|Number=Sing),\n", " ('end', ),\n", " ('Kevin', Gender=Masc|Number=Sing),\n", " ('Boss', Number=Sing),\n", " (',', ),\n", " ('para', ),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('incrível', Gender=Masc|Number=Sing),\n", " ('avanço', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('45', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('que', Gender=Masc|Number=Sing|PronType=Rel),\n", " ('deixou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('time', Gender=Masc|Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('35', NumType=Card),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Gender=Masc|Number=Plur),\n", " ('.', ),\n", " ('Outro', Gender=Masc|Number=Sing|PronType=Ind),\n", " ('lançamento', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('desta', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('vez', Gender=Fem|Number=Sing),\n", " ('para', ),\n", " ('Steve', Gender=Masc|Number=Sing),\n", " ('Smith', Number=Sing),\n", " (',', ),\n", " ('marcou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('avanço', Gender=Masc|Number=Sing),\n", " ('até', ),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('12', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('.', ),\n", " ('Duas', NumType=Card),\n", " ('jogadas', Gender=Fem|Number=Plur),\n", " ('depois', ),\n", " (',', ),\n", " ('David', Gender=Masc|Number=Sing),\n", " ('Tyree', Number=Sing),\n", " ('pegou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('passe', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('cinco', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('end', ),\n", " ('zone', ),\n", " ('para', ),\n", " ('anotar', VerbForm=Inf),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('touchdown', Gender=Masc|Number=Sing),\n", " ('e', ),\n", " ('virar', VerbForm=Inf),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('jogo', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('hora', Gender=Fem|Number=Sing),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('decisão', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('ataque', Gender=Masc|Number=Sing),\n", " ('dos', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Patriots', Number=Sing),\n", " ('voltou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('a', ),\n", " ('funcionar', VerbForm=Inf),\n", " ('.', ),\n", " ('Com', ),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('série', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('passes', Gender=Masc|Number=Plur),\n", " ('curtos', Gender=Masc|Number=Plur),\n", " ('e', ),\n", " ('variados', Gender=Masc|Number=Plur),\n", " (',', ),\n", " ('Brady', Gender=Masc|Number=Sing),\n", " ('achou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('Wes', Gender=Masc|Number=Sing),\n", " ('Welker', Number=Sing),\n", " (',', ),\n", " ('Randy', Gender=Masc|Number=Sing),\n", " ('Moss', Number=Sing),\n", " ('e', ),\n", " ('Kevin', Gender=Masc|Number=Sing),\n", " ('Faulk', Number=Sing),\n", " ('seguidas', Gender=Fem|Number=Plur|VerbForm=Part),\n", " ('vezes', Gender=Fem|Number=Plur),\n", " ('até', ),\n", " ('chegar', VerbForm=Inf),\n", " ('à', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('red', Gender=Masc|Number=Sing),\n", " ('zone', Gender=Masc|Number=Sing),\n", " ('.', ),\n", " ('A', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('2m45s', Gender=Fem|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fim', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('quarterback', Gender=Masc|Number=Sing),\n", " ('conectou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('mais', ),\n", " ('uma', ),\n", " ('vez', Gender=Fem|Number=Sing),\n", " ('com', ),\n", " ('Moss', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('que', Gender=Masc|Number=Sing|PronType=Rel),\n", " ('se', Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs),\n", " ('desmarcou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('e', ),\n", " ('ficou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('livre', Gender=Fem|Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('lateral', Gender=Fem|Number=Sing),\n", " ('direita', Gender=Fem|Number=Sing),\n", " ('da', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('end', ),\n", " ('zone', ),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Quando', ),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('fãs', Gender=Masc|Number=Plur),\n", " ('de', ),\n", " ('New', Gender=Masc|Number=Sing),\n", " ('England', Number=Sing),\n", " ('já', ),\n", " ('comemoravam', Mood=Ind|Number=Plur|Person=3|Tense=Imp|VerbForm=Fin),\n", " ('a', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('vitória', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('inesperado', Gender=Masc|Number=Sing),\n", " ('aconteceu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('.', ),\n", " ('Em', ),\n", " ('uma', Definite=Ind|Gender=Fem|Number=Sing|PronType=Art),\n", " ('jogada', Gender=Fem|Number=Sing),\n", " ('incrível', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('Eli', Gender=Masc|Number=Sing),\n", " ('Manning', Number=Sing),\n", " ('se', Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs),\n", " ('soltou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('de', ),\n", " ('dois', NumType=Card),\n", " ('marcadores', Gender=Masc|Number=Plur),\n", " ('que', Gender=Masc|Number=Plur|PronType=Rel),\n", " ('o', Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs),\n", " ('seguravam', Mood=Ind|Number=Plur|Person=3|Tense=Imp|VerbForm=Fin),\n", " ('pela', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('camisa', Gender=Fem|Number=Sing),\n", " ('e', ),\n", " (',', ),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('corrida', Gender=Fem|Number=Sing),\n", " (',', ),\n", " ('lançou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('para', ),\n", " ('Amani', Gender=Masc|Number=Sing),\n", " ('Toomer', Number=Sing),\n", " ('.', ),\n", " ('O', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('wide', Gender=Masc|Number=Sing),\n", " ('receiver', ),\n", " (',', ),\n", " ('bem', ),\n", " ('marcado', Gender=Masc|Number=Sing|VerbForm=Part),\n", " (',', ),\n", " ('saltou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('e', ),\n", " ('conseguiu', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('a', ),\n", " ('fazer', VerbForm=Inf),\n", " ('recepção', Gender=Fem|Number=Sing),\n", " ('para', ),\n", " ('um', Definite=Ind|Gender=Masc|Number=Sing|PronType=Art),\n", " ('avanço', Gender=Masc|Number=Sing),\n", " ('de', ),\n", " ('32', NumType=Card),\n", " ('jardas', Gender=Fem|Number=Plur),\n", " (',', ),\n", " ('deixando', VerbForm=Ger),\n", " ('os', Definite=Def|Gender=Masc|Number=Plur|PronType=Art),\n", " ('Giants', Gender=Masc|Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('linha', Gender=Fem|Number=Sing),\n", " ('de', ),\n", " ('24', NumType=Card),\n", " ('de', ),\n", " ('New', Gender=Masc|Number=Sing),\n", " ('England', Number=Sing),\n", " ('.', ),\n", " ('\\n\\n', ),\n", " ('Quatro', NumType=Card),\n", " ('jogadas', Gender=Fem|Number=Plur),\n", " ('depois', ),\n", " (',', ),\n", " ('a', ),\n", " ('39', NumType=Card),\n", " ('segundos', Gender=Masc|Number=Plur),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('fim', Gender=Masc|Number=Sing),\n", " (',', ),\n", " ('Manning', Gender=Masc|Number=Sing),\n", " ('achou', Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin),\n", " ('Plaxico', Gender=Masc|Number=Sing),\n", " ('Burress', Number=Sing),\n", " ('na', Definite=Def|Gender=Fem|Number=Sing|PronType=Art),\n", " ('end', Number=Sing),\n", " ('zone', ),\n", " ('para', ),\n", " ('conseguir', VerbForm=Inf),\n", " ('o', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('touchdown', Gender=Masc|Number=Sing),\n", " ('do', Definite=Def|Gender=Masc|Number=Sing|PronType=Art),\n", " ('título', Gender=Masc|Number=Sing),\n", " ('.', )]" ] }, "metadata": {}, "execution_count": 23 } ] }, { "cell_type": "markdown", "metadata": { "id": "Cy719af698_l" }, "source": [ "**Reconhecimento de Entidades Nomeadas**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "YJVbQJL8SKr1", "outputId": "ee4d004e-3c87-4947-daab-624acd903b9b" }, "source": [ "entidades_nomeadas = list(doc.ents)\n", "print(entidades_nomeadas)\n", "\n", "detalhes_entidades = [(entidade, entidade.label_) for entidade in doc.ents]\n", "detalhes_entidades" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "[Giants, Patriots, Super Bowl XLII\n", ", Azarões, New England, Eli Manning, Plaxico Burress, New York Giants, New England Patriots, Glendale, Super Bowl XLII, Super Bowl, Tom Brady, NFL, Giants, Super Bowl, Peyton Manning, Eli, NFL, Indianapolis Colts, Giants, Brandon Jacobs, Nova York, red zone, Lawrence Tynes, Eli Manning, Patriots, Laurence Maroney, Tom Brady, Patriots, Antonio Pierce, Maroney, Giants, Manning, Amani Toomer, Nova York, red zone, Patriots, Giants, Manning, Steve Smith, Ellis Hobbs, Patriots, Nova York, Giants, Nova York, Manning, Patriots, Brady, Giants, Manning, Patriots, Giants, Bill Bellichick, Brady, Jabar Gaffney, Giants, Manning, Kevin Boss, Patriots, Steve Smith, David Tyree, end zone, Patriots, Brady, Wes Welker, Randy Moss, Kevin Faulk, red zone, Moss, end zone, New England, Eli Manning, Amani Toomer, Giants, New England, Manning, Plaxico Burress, end zone]\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "[(Giants, 'ORG'),\n", " (Patriots, 'MISC'),\n", " (Super Bowl XLII, 'ORG'),\n", " (Azarões, 'LOC'),\n", " (New England, 'LOC'),\n", " (Eli Manning, 'PER'),\n", " (Plaxico Burress, 'PER'),\n", " (New York Giants, 'ORG'),\n", " (New England Patriots, 'MISC'),\n", " (Glendale, 'LOC'),\n", " (Super Bowl XLII, 'ORG'),\n", " (Super Bowl, 'ORG'),\n", " (Tom Brady, 'PER'),\n", " (NFL, 'ORG'),\n", " (Giants, 'ORG'),\n", " (Super Bowl, 'ORG'),\n", " (Peyton Manning, 'PER'),\n", " (Eli, 'PER'),\n", " (NFL, 'ORG'),\n", " (Indianapolis Colts, 'ORG'),\n", " (Giants, 'ORG'),\n", " (Brandon Jacobs, 'PER'),\n", " (Nova York, 'LOC'),\n", " (red zone, 'ORG'),\n", " (Lawrence Tynes, 'PER'),\n", " (Eli Manning, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Laurence Maroney, 'PER'),\n", " (Tom Brady, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Antonio Pierce, 'PER'),\n", " (Maroney, 'PER'),\n", " (Giants, 'ORG'),\n", " (Manning, 'PER'),\n", " (Amani Toomer, 'PER'),\n", " (Nova York, 'LOC'),\n", " (red zone, 'ORG'),\n", " (Patriots, 'MISC'),\n", " (Giants, 'ORG'),\n", " (Manning, 'PER'),\n", " (Steve Smith, 'PER'),\n", " (Ellis Hobbs, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Nova York, 'LOC'),\n", " (Giants, 'ORG'),\n", " (Nova York, 'LOC'),\n", " (Manning, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Brady, 'PER'),\n", " (Giants, 'ORG'),\n", " (Manning, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Giants, 'ORG'),\n", " (Bill Bellichick, 'PER'),\n", " (Brady, 'PER'),\n", " (Jabar Gaffney, 'PER'),\n", " (Giants, 'ORG'),\n", " (Manning, 'PER'),\n", " (Kevin Boss, 'PER'),\n", " (Patriots, 'MISC'),\n", " (Steve Smith, 'PER'),\n", " (David Tyree, 'PER'),\n", " (end zone, 'ORG'),\n", " (Patriots, 'MISC'),\n", " (Brady, 'PER'),\n", " (Wes Welker, 'PER'),\n", " (Randy Moss, 'PER'),\n", " (Kevin Faulk, 'PER'),\n", " (red zone, 'ORG'),\n", " (Moss, 'PER'),\n", " (end zone, 'ORG'),\n", " (New England, 'LOC'),\n", " (Eli Manning, 'PER'),\n", " (Amani Toomer, 'PER'),\n", " (Giants, 'ORG'),\n", " (New England, 'LOC'),\n", " (Manning, 'PER'),\n", " (Plaxico Burress, 'PER'),\n", " (end zone, 'ORG')]" ] }, "metadata": {}, "execution_count": 26 } ] }, { "cell_type": "markdown", "metadata": { "id": "uUVfKsRe-BfW" }, "source": [ "**Vamos visualizar as entidades!**" ] }, { "cell_type": "code", "metadata": { "id": "SNzLf69UUTgr" }, "source": [ "html = spacy.displacy.render(doc, style=\"ent\")\n", "output_path = open('entidades_nomadas.html', 'w', encoding=\"utf-8\")\n", "output_path.write(html)\n", "output_path.close()" ], "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "metadata": { "id": "p9K86DrX-FiW" }, "source": [ "**Análise sintática de dependências**" ] }, { "cell_type": "code", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "LHbJhaafVISC", "outputId": "fb8b5ac1-2bd5-4451-b7b8-6e9a4177635f" }, "source": [ "sintaxe = [(token.orth_, token.dep_) for token in doc]\n", "print(sintaxe)" ], "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "[('Giants', 'nsubj'), ('batem', 'ROOT'), ('os', 'det'), ('Patriots', 'obj'), ('no', 'case'), ('Super', 'obl'), ('Bowl', 'flat:name'), ('XLII', 'flat:name'), ('\\n', 'dep'), ('Azarões', 'flat:name'), ('acabam', 'conj'), ('com', 'case'), ('a', 'det'), ('invencibilidade', 'obl'), ('de', 'case'), ('New', 'nmod'), ('England', 'flat:name'), ('e', 'cc'), ('ficam', 'conj'), ('com', 'case'), ('o', 'det'), ('título', 'obl'), ('da', 'case'), ('temporada', 'nmod'), ('\\n', 'aux:pass'), ('04/02/2008', 'obl'), ('-', 'punct'), ('01h07', 'obl'), ('m', 'obj'), ('-', 'punct'), ('Atualizado', 'acl'), ('em', 'case'), ('04/02/2008', 'obl'), ('-', 'punct'), ('09h49', 'nsubj'), ('m', 'punct'), ('\\n\\n', 'parataxis'), ('Com', 'case'), ('um', 'det'), ('passe', 'nmod'), ('de', 'case'), ('Eli', 'nmod'), ('Manning', 'flat:name'), ('para', 'case'), ('Plaxico', 'nmod'), ('Burress', 'flat:name'), ('a', 'case'), ('39', 'nummod'), ('segundos', 'nmod'), ('do', 'case'), ('fim', 'nmod'), (',', 'punct'), ('o', 'det'), ('New', 'nsubj'), ('York', 'flat:name'), ('Giants', 'flat:name'), ('anotou', 'ROOT'), ('o', 'det'), ('touchdown', 'obj'), ('decisivo', 'amod'), ('e', 'cc'), ('derrubou', 'conj'), ('o', 'det'), ('favorito', 'obj'), ('New', 'appos'), ('England', 'flat:name'), ('Patriots', 'flat:name'), ('por', 'case'), ('17', 'obl'), ('a', 'case'), ('14', 'nmod'), ('neste', 'case'), ('domingo', 'nmod'), (',', 'punct'), ('em', 'case'), ('Glendale', 'obl'), (',', 'punct'), ('no', 'case'), ('Super', 'obl'), ('Bowl', 'flat:name'), ('XLII', 'flat:name'), ('.', 'punct'), ('O', 'det'), ('resultado', 'nsubj'), (',', 'punct'), ('uma', 'appos'), ('das', 'case'), ('maiores', 'amod'), ('zebras', 'nmod'), ('da', 'case'), ('história', 'nmod'), ('do', 'case'), ('Super', 'nmod'), ('Bowl', 'flat:name'), (',', 'punct'), ('acabou', 'ROOT'), ('com', 'case'), ('a', 'det'), ('temporada', 'obl'), ('perfeita', 'amod'), ('de', 'case'), ('Tom', 'nmod'), ('Brady', 'flat:name'), ('e', 'cc'), ('companhia', 'conj'), (',', 'punct'), ('que', 'nsubj'), ('esperavam', 'acl:relcl'), ('fazer', 'xcomp'), ('história', 'obj'), ('ao', 'mark'), ('levantar', 'advcl'), ('o', 'det'), ('troféu', 'obj'), ('da', 'case'), ('NFL', 'nmod'), ('sem', 'mark'), ('sofrer', 'advcl'), ('uma', 'det'), ('derrota', 'obj'), ('no', 'case'), ('ano', 'nmod'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('A', 'det'), ('vitória', 'nsubj'), ('dos', 'case'), ('Giants', 'nmod'), (',', 'punct'), ('porém', 'cc'), (',', 'punct'), ('também', 'advmod'), ('ficará', 'ROOT'), ('para', 'case'), ('a', 'det'), ('história', 'obl'), ('.', 'punct'), ('Pela', 'obl'), ('primeira', 'case'), ('vez', 'nmod'), (',', 'punct'), ('irmãos', 'nsubj'), ('quarterbacks', 'appos'), ('triunfam', 'ROOT'), ('no', 'case'), ('Super', 'obl'), ('Bowl', 'flat:name'), ('em', 'case'), ('temporadas', 'obl'), ('consecutivas', 'amod'), ('.', 'punct'), ('No', 'case'), ('ano', 'obl'), ('passado', 'amod'), (',', 'punct'), ('Peyton', 'nsubj'), ('Manning', 'flat:name'), (',', 'punct'), ('irmão', 'appos'), ('de', 'case'), ('Eli', 'nmod'), (',', 'punct'), ('chegou', 'ROOT'), ('ao', 'case'), ('título', 'obl'), ('máximo', 'amod'), ('da', 'case'), ('NFL', 'nmod'), ('pelo', 'case'), ('Indianapolis', 'nmod'), ('Colts', 'flat:name'), ('.', 'punct'), ('\\n\\n', 'ROOT'), ('A', 'det'), ('partida', 'nsubj'), ('\\n\\n', 'advmod'), ('Os', 'det'), ('Giants', 'nsubj'), ('começaram', 'ROOT'), ('com', 'case'), ('a', 'det'), ('posse', 'obl'), ('de', 'case'), ('bola', 'nmod'), (',', 'punct'), ('e', 'cc'), ('mostraram', 'conj'), ('logo', 'advmod'), ('que', 'mark'), ('iriam', 'aux'), ('alongar', 'ccomp'), ('ao', 'case'), ('máximo', 'obl'), ('suas', 'det'), ('posses', 'obj'), ('de', 'case'), ('bola', 'nmod'), ('.', 'punct'), ('Misturando', 'advcl'), ('corridas', 'obj'), ('com', 'case'), ('Brandon', 'nmod'), ('Jacobs', 'flat:name'), ('e', 'cc'), ('passes', 'conj'), ('curtos', 'amod'), (',', 'punct'), ('o', 'det'), ('time', 'nsubj'), ('de', 'case'), ('Nova', 'nmod'), ('York', 'flat:name'), ('chegou', 'ROOT'), ('à', 'case'), ('red', 'amod'), ('zone', 'obl'), ('logo', 'advmod'), ('na', 'case'), ('primeira', 'amod'), ('campanha', 'obl'), ('.', 'punct'), ('O', 'det'), ('avanço', 'nsubj'), (',', 'punct'), ('no', 'cc'), ('entanto', 'fixed'), (',', 'punct'), ('parou', 'ROOT'), ('na', 'case'), ('linha', 'obl'), ('de', 'case'), ('17', 'nummod'), ('jardas', 'nmod'), ('e', 'cc'), ('Lawrence', 'conj'), ('Tynes', 'flat:name'), ('converteu', 'conj'), ('o', 'det'), ('field', 'obj'), ('goal', 'flat:name'), ('de', 'case'), ('32', 'nummod'), ('jardas', 'nmod'), ('para', 'mark'), ('abrir', 'advcl'), ('o', 'det'), ('placar', 'obj'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('Eli', 'nsubj'), ('Manning', 'flat:name'), ('e', 'cc'), ('companhia', 'conj'), ('ficaram', 'ROOT'), ('9m54s', 'obj'), ('com', 'case'), ('a', 'det'), ('bola', 'nmod'), (',', 'punct'), ('mas', 'cc'), ('o', 'det'), ('ataque', 'nsubj'), ('dos', 'case'), ('Patriots', 'nmod'), ('não', 'advmod'), ('entrou', 'conj'), ('em', 'case'), ('campo', 'obl'), ('frio', 'amod'), ('.', 'punct'), ('Logo', 'advmod'), ('no', 'case'), ('retorno', 'obl'), ('do', 'case'), ('kickoff', 'nmod'), (',', 'punct'), ('o', 'det'), ('running', 'ROOT'), ('back', 'amod'), ('Laurence', 'nsubj'), ('Maroney', 'flat:name'), ('avançou', 'ROOT'), ('43', 'nummod'), ('jardas', 'obj'), (',', 'punct'), ('deixando', 'advcl'), ('Tom', 'obj'), ('Brady', 'flat:name'), ('em', 'case'), ('boa', 'amod'), ('posição', 'obl'), ('.', 'punct'), ('Com', 'case'), ('passes', 'obl'), ('curtos', 'amod'), (',', 'punct'), ('os', 'det'), ('Patriots', 'nsubj'), ('chegaram', 'ROOT'), ('à', 'case'), ('linha', 'obl'), ('de', 'case'), ('17', 'nummod'), ('jardas', 'nmod'), ('e', 'cc'), (',', 'punct'), ('graças', 'case'), ('a', 'det'), ('uma', 'det'), ('penalidade', 'obl'), ('(', 'punct'), ('interferência', 'appos'), ('de', 'case'), ('passe', 'nmod'), (')', 'punct'), ('do', 'case'), ('linebacker', 'nmod'), ('Antonio', 'appos'), ('Pierce', 'flat:name'), (',', 'punct'), ('alcançaram', 'conj'), ('a', 'det'), ('linha', 'obj'), ('de', 'case'), ('uma', 'det'), ('jarda', 'nmod'), ('.', 'punct'), ('Maroney', 'nsubj'), ('avançou', 'ROOT'), ('pelo', 'case'), ('chão', 'obl'), ('e', 'cc'), ('anotou', 'conj'), ('o', 'det'), ('primeiro', 'amod'), ('touchdown', 'obj'), ('do', 'case'), ('jogo', 'nmod'), ('.', 'punct'), ('\\n\\n', 'ROOT'), ('Os', 'det'), ('Giants', 'nsubj'), ('pareciam', 'ROOT'), ('rumo', 'advmod'), ('à', 'case'), ('virada', 'obl'), ('na', 'case'), ('campanha', 'nmod'), ('seguinte', 'amod'), ('.', 'punct'), ('Manning', 'nsubj'), ('achou', 'ROOT'), ('Amani', 'obj'), ('Toomer', 'flat:name'), ('para', 'case'), ('um', 'det'), ('avanço', 'obl'), ('de', 'case'), ('38', 'nummod'), ('jardas', 'nmod'), (',', 'punct'), ('e', 'cc'), ('o', 'det'), ('time', 'conj'), ('de', 'case'), ('Nova', 'nmod'), ('York', 'flat:name'), ('entrou', 'conj'), ('novamente', 'advmod'), ('na', 'case'), ('red', 'amod'), ('zone', 'obl'), ('.', 'punct'), ('Com', 'case'), ('a', 'det'), ('bola', 'obl'), ('na', 'case'), ('linha', 'nmod'), ('de', 'case'), ('14', 'nummod'), ('jardas', 'nmod'), ('dos', 'case'), ('Patriots', 'nmod'), (',', 'punct'), ('os', 'det'), ('Giants', 'nsubj'), ('sofreram', 'ROOT'), ('um', 'det'), ('revés', 'obj'), ('.', 'punct'), ('Manning', 'nsubj'), ('passou', 'ROOT'), ('para', 'case'), ('Steve', 'obl'), ('Smith', 'flat:name'), (',', 'punct'), ('que', 'nsubj'), ('soltou', 'acl:relcl'), ('a', 'det'), ('bola', 'obj'), ('.', 'punct'), ('Ellis', 'nsubj'), ('Hobbs', 'flat:name'), ('aproveitou', 'ROOT'), (',', 'punct'), ('tomou', 'conj'), ('a', 'det'), ('posse', 'obj'), ('para', 'case'), ('os', 'det'), ('Patriots', 'nmod'), (',', 'punct'), ('e', 'cc'), ('avançou', 'conj'), ('23', 'nummod'), ('jardas', 'obj'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('A', 'det'), ('defesa', 'nsubj'), ('de', 'case'), ('Nova', 'nmod'), ('York', 'flat:name'), ('manteve', 'ROOT'), ('o', 'det'), ('jogo', 'obj'), ('equilibrado', 'amod'), ('.', 'punct'), ('Com', 'case'), ('dois', 'nummod'), ('sacks', 'obl'), ('seguidos', 'acl'), (',', 'punct'), ('os', 'det'), ('Giants', 'nsubj'), ('forçaram', 'ROOT'), ('o', 'det'), ('punt', 'obj'), ('e', 'cc'), ('recuperaram', 'conj'), ('a', 'det'), ('bola', 'obj'), ('.', 'punct'), ('Mas', 'cc'), ('a', 'det'), ('campanha', 'nsubj'), ('seguinte', 'amod'), ('provou', 'ROOT'), ('ser', 'cop'), ('outra', 'det'), ('decepção', 'xcomp'), ('para', 'case'), ('Nova', 'nmod'), ('York', 'flat:name'), ('.', 'punct'), ('O', 'det'), ('time', 'nsubj'), ('chegou', 'ROOT'), ('à', 'case'), ('linha', 'obl'), ('de', 'case'), ('25', 'nummod'), ('jardas', 'nmod'), (',', 'punct'), ('mas', 'cc'), ('Manning', 'nsubj'), ('sofreu', 'conj'), ('um', 'det'), ('sack', 'obj'), ('e', 'cc'), ('cometeu', 'conj'), ('um', 'det'), ('fumble', 'obj'), (',', 'punct'), ('e', 'cc'), ('o', 'det'), ('ataque', 'nsubj'), ('voltou', 'conj'), ('para', 'case'), ('a', 'det'), ('linha', 'obl'), ('de', 'case'), ('39', 'nummod'), ('jardas', 'nmod'), (',', 'punct'), ('não', 'advmod'), ('conseguindo', 'advcl'), ('pontuar', 'xcomp'), ('mais', 'obl'), ('uma', 'case'), ('vez', 'obl'), ('.', 'punct'), ('\\n\\n', 'ROOT'), ('Os', 'det'), ('Patriots', 'nsubj'), ('tiveram', 'ROOT'), ('uma', 'det'), ('última', 'amod'), ('chance', 'obj'), ('de', 'mark'), ('marcar', 'acl'), ('antes', 'advmod'), ('do', 'case'), ('intervalo', 'obl'), (',', 'punct'), ('mas', 'cc'), (',', 'punct'), ('a', 'case'), ('22', 'nummod'), ('segundos', 'obl'), ('do', 'case'), ('fim', 'nmod'), ('do', 'case'), ('segundo', 'amod'), ('período', 'nmod'), (',', 'punct'), ('Brady', 'nsubj'), ('foi', 'aux:pass'), ('novamente', 'advmod'), ('sacado', 'conj'), ('.', 'punct'), ('Desta', 'case'), ('vez', 'obl'), (',', 'punct'), ('ele', 'nsubj'), ('cometeu', 'ROOT'), ('o', 'det'), ('fumble', 'obj'), ('e', 'cc'), ('os', 'det'), ('Giants', 'nsubj'), ('tomaram', 'conj'), ('a', 'det'), ('posse', 'obj'), ('de', 'case'), ('bola', 'nmod'), ('.', 'punct'), ('Manning', 'nsubj'), ('tentou', 'ROOT'), ('um', 'det'), ('passe', 'obj'), ('longo', 'amod'), (',', 'punct'), ('de', 'case'), ('50', 'nummod'), ('jardas', 'obl'), (',', 'punct'), ('nos', 'case'), ('últimos', 'amod'), ('segundos', 'obl'), (',', 'punct'), ('mas', 'cc'), ('não', 'advmod'), ('teve', 'conj'), ('sucesso', 'obj'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('O', 'det'), ('jogo', 'nsubj'), ('continuou', 'ROOT'), ('amarrado', 'xcomp'), ('no', 'case'), ('terceiro', 'amod'), ('quarto', 'obl'), (',', 'punct'), ('com', 'case'), ('as', 'det'), ('defesas', 'obl'), ('levando', 'acl'), ('a', 'det'), ('melhor', 'obj'), ('sobre', 'case'), ('os', 'det'), ('ataques', 'obl'), ('.', 'punct'), ('A', 'det'), ('única', 'amod'), ('chance', 'nsubj'), ('de', 'mark'), ('pontuar', 'acl'), ('do', 'case'), ('período', 'obl'), ('foi', 'cop'), ('dos', 'case'), ('Patriots', 'ROOT'), (',', 'punct'), ('que', 'nsubj'), ('chegaram', 'acl:relcl'), ('à', 'case'), ('linha', 'obl'), ('de', 'case'), ('31', 'nummod'), ('jardas', 'nmod'), ('dos', 'case'), ('Giants', 'nmod'), ('.', 'punct'), ('O', 'det'), ('técnico', 'nsubj'), ('Bill', 'appos'), ('Bellichick', 'flat:name'), (',', 'punct'), ('porém', 'cc'), (',', 'punct'), ('optou', 'ROOT'), ('por', 'case'), ('uma', 'det'), ('quarta', 'amod'), ('descida', 'obl'), ('em', 'case'), ('vez', 'obl'), ('de', 'case'), ('um', 'det'), ('field', 'obj'), ('goal', 'amod'), ('.', 'punct'), ('Brady', 'nsubj'), ('tentou', 'ROOT'), ('um', 'det'), ('passe', 'obj'), ('para', 'case'), ('Jabar', 'obl'), ('Gaffney', 'flat:name'), (',', 'punct'), ('mas', 'cc'), ('não', 'advmod'), ('conseguiu', 'conj'), ('completar', 'xcomp'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('O', 'det'), ('último', 'amod'), ('período', 'nsubj'), ('começou', 'ROOT'), ('arrasador', 'xcomp'), ('para', 'case'), ('os', 'det'), ('Giants', 'obl'), ('.', 'punct'), ('na', 'case'), ('primeira', 'amod'), ('jogada', 'obl'), (',', 'punct'), ('Manning', 'nsubj'), ('achou', 'ROOT'), ('o', 'det'), ('tight', 'obj'), ('end', 'flat:name'), ('Kevin', 'appos'), ('Boss', 'flat:name'), (',', 'punct'), ('para', 'case'), ('um', 'det'), ('incrível', 'amod'), ('avanço', 'obl'), ('de', 'case'), ('45', 'nummod'), ('jardas', 'nmod'), (',', 'punct'), ('que', 'nsubj'), ('deixou', 'acl:relcl'), ('o', 'det'), ('time', 'obj'), ('na', 'case'), ('linha', 'obl'), ('de', 'case'), ('35', 'nmod'), ('dos', 'case'), ('Patriots', 'nmod'), ('.', 'punct'), ('Outro', 'det'), ('lançamento', 'nsubj'), (',', 'punct'), ('desta', 'case'), ('vez', 'nmod'), ('para', 'case'), ('Steve', 'nmod'), ('Smith', 'flat:name'), (',', 'punct'), ('marcou', 'ROOT'), ('o', 'det'), ('avanço', 'obj'), ('até', 'case'), ('a', 'det'), ('linha', 'obl'), ('de', 'case'), ('12', 'nummod'), ('jardas', 'nmod'), ('.', 'punct'), ('Duas', 'nummod'), ('jogadas', 'obl'), ('depois', 'advmod'), (',', 'punct'), ('David', 'nsubj'), ('Tyree', 'flat:name'), ('pegou', 'ROOT'), ('um', 'det'), ('passe', 'obj'), ('de', 'case'), ('cinco', 'nummod'), ('jardas', 'nmod'), ('na', 'case'), ('end', 'nmod'), ('zone', 'flat:name'), ('para', 'mark'), ('anotar', 'advcl'), ('o', 'det'), ('touchdown', 'obj'), ('e', 'cc'), ('virar', 'conj'), ('o', 'det'), ('jogo', 'obj'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('Na', 'case'), ('hora', 'obl'), ('da', 'case'), ('decisão', 'nmod'), (',', 'punct'), ('o', 'det'), ('ataque', 'nsubj'), ('dos', 'case'), ('Patriots', 'nmod'), ('voltou', 'ROOT'), ('a', 'mark'), ('funcionar', 'xcomp'), ('.', 'punct'), ('Com', 'case'), ('uma', 'det'), ('série', 'obl'), ('de', 'case'), ('passes', 'nmod'), ('curtos', 'amod'), ('e', 'cc'), ('variados', 'conj'), (',', 'punct'), ('Brady', 'nsubj'), ('achou', 'ROOT'), ('Wes', 'obj'), ('Welker', 'flat:name'), (',', 'punct'), ('Randy', 'dep'), ('Moss', 'flat:name'), ('e', 'cc'), ('Kevin', 'conj'), ('Faulk', 'flat:name'), ('seguidas', 'xcomp'), ('vezes', 'obj'), ('até', 'mark'), ('chegar', 'advcl'), ('à', 'case'), ('red', 'amod'), ('zone', 'obl'), ('.', 'punct'), ('A', 'case'), ('2m45s', 'obl'), ('do', 'case'), ('fim', 'nmod'), (',', 'punct'), ('o', 'det'), ('quarterback', 'nsubj'), ('conectou', 'ROOT'), ('mais', 'advmod'), ('uma', 'case'), ('vez', 'obl'), ('com', 'case'), ('Moss', 'obl'), (',', 'punct'), ('que', 'nsubj'), ('se', 'expl'), ('desmarcou', 'acl:relcl'), ('e', 'cc'), ('ficou', 'conj'), ('livre', 'xcomp'), ('na', 'case'), ('lateral', 'obl'), ('direita', 'amod'), ('da', 'case'), ('end', 'nmod'), ('zone', 'flat:name'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('Quando', 'mark'), ('os', 'det'), ('fãs', 'nsubj'), ('de', 'case'), ('New', 'nmod'), ('England', 'flat:name'), ('já', 'advmod'), ('comemoravam', 'advcl'), ('a', 'det'), ('vitória', 'obj'), (',', 'punct'), ('o', 'det'), ('inesperado', 'nsubj'), ('aconteceu', 'ROOT'), ('.', 'punct'), ('Em', 'case'), ('uma', 'det'), ('jogada', 'obl'), ('incrível', 'amod'), (',', 'punct'), ('Eli', 'nsubj'), ('Manning', 'flat:name'), ('se', 'expl'), ('soltou', 'ROOT'), ('de', 'case'), ('dois', 'nummod'), ('marcadores', 'obj'), ('que', 'nsubj'), ('o', 'obj'), ('seguravam', 'acl:relcl'), ('pela', 'case'), ('camisa', 'obl'), ('e', 'cc'), (',', 'punct'), ('na', 'case'), ('corrida', 'obl'), (',', 'punct'), ('lançou', 'conj'), ('para', 'case'), ('Amani', 'obl'), ('Toomer', 'flat:name'), ('.', 'punct'), ('O', 'det'), ('wide', 'nsubj'), ('receiver', 'flat:name'), (',', 'punct'), ('bem', 'advmod'), ('marcado', 'acl'), (',', 'punct'), ('saltou', 'ROOT'), ('e', 'cc'), ('conseguiu', 'conj'), ('a', 'mark'), ('fazer', 'xcomp'), ('recepção', 'obj'), ('para', 'case'), ('um', 'det'), ('avanço', 'nmod'), ('de', 'case'), ('32', 'nummod'), ('jardas', 'nmod'), (',', 'punct'), ('deixando', 'advcl'), ('os', 'det'), ('Giants', 'obj'), ('na', 'case'), ('linha', 'obl'), ('de', 'case'), ('24', 'nmod'), ('de', 'case'), ('New', 'nmod'), ('England', 'flat:name'), ('.', 'punct'), ('\\n\\n', 'advmod'), ('Quatro', 'nummod'), ('jogadas', 'obl'), ('depois', 'advmod'), (',', 'punct'), ('a', 'case'), ('39', 'nummod'), ('segundos', 'obl'), ('do', 'case'), ('fim', 'nmod'), (',', 'punct'), ('Manning', 'nsubj'), ('achou', 'ROOT'), ('Plaxico', 'obj'), ('Burress', 'flat:name'), ('na', 'case'), ('end', 'obl'), ('zone', 'flat:name'), ('para', 'mark'), ('conseguir', 'advcl'), ('o', 'det'), ('touchdown', 'obj'), ('do', 'case'), ('título', 'nmod'), ('.', 'punct')]\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "pP7o939i-IWt" }, "source": [ "**Vamos visualizar a árvore de dependências**" ] }, { "cell_type": "code", "metadata": { "id": "1QvmBR5MVYg3" }, "source": [ "visualizar_sintaxe = spacy.displacy.render(doc, style='dep')\n", "output_path = open('analise_dependencia.svg', 'w', encoding=\"utf-8\")\n", "output_path.write(visualizar_sintaxe)\n", "output_path.close()" ], "execution_count": null, "outputs": [] } ] }