{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "source": [ "import spacy\n", "from spacy.tokens import Doc\n", "from spacy.matcher import Matcher\n", "from spacy import displacy" ], "metadata": { "collapsed": true, "id": "9S51okBYzsjH" }, "execution_count": 4, "outputs": [] }, { "cell_type": "code", "source": [ "\n", "\n", "nlp = spacy.load(\"en_core_web_sm\")\n", "\n", "def information_extraction(doc):\n", " matcher = Matcher(nlp.vocab)\n", "\n", " svo_pattern = [\n", " {\"DEP\": \"nsubj\"},\n", " {\"DEP\": \"aux\", \"OP\": \"?\"},\n", " {\"POS\": \"VERB\"},\n", " {\"DEP\": \"det\", \"OP\": \"?\"},\n", " {\"DEP\": {\"IN\": [\"dobj\", \"attr\", \"pobj\"]}}\n", " ]\n", "\n", " matcher.add(\"SVO_PATTERN\", [svo_pattern])\n", " matches = matcher(doc)\n", "\n", " relations = []\n", " for _, start, end in matches:\n", " span = doc[start:end]\n", " subj = span[0].text\n", " verb = span[2].lemma_\n", " obj = span[-1].text\n", " relations.append((subj, verb, obj))\n", "\n", " return relations\n", "\n" ], "metadata": { "collapsed": true, "id": "rQzVnbwF4Ckx" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "\n", "Doc.set_extension(\"relations\", getter=information_extraction, force=True)\n", "\n", "text = \"Apple is acquiring a U.K. startup. Sundar Pichai is the CEO of Google.\"\n", "\n", "doc = nlp(text)\n", "\n", "print(\"Named Entities:\")\n", "for ent in doc.ents:\n", " print(f\"{ent.text} --> {ent.label_}\")\n", "\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "URMl3s5s4Cm7", "outputId": "edf8df08-4f2e-4bbb-b34e-9635f95db72c" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Named Entities:\n", "Apple --> ORG\n", "U.K. --> GPE\n", "Sundar Pichai --> PERSON\n", "Google --> ORG\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "print(\"\\nExtracted Relations (SVO):\")\n", "for rel in doc._.relations:\n", " print(rel)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "oa5O-NzP4CpZ", "outputId": "47fb5d31-433e-4714-fc64-223c90c66b89" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Extracted Relations (SVO):\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "displacy.render(doc, style=\"dep\", jupyter=True)\n", "displacy.render(doc, style=\"ent\", jupyter=True)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 475 }, "id": "qMlr-Wgz4CsC", "outputId": "1547767f-1815-469b-df74-01b473326dc0" }, "execution_count": 10, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", "\n", " Apple\n", " PROPN\n", "\n", "\n", "\n", " is\n", " AUX\n", "\n", "\n", "\n", " acquiring\n", " VERB\n", "\n", "\n", "\n", " a\n", " DET\n", "\n", "\n", "\n", " U.K.\n", " PROPN\n", "\n", "\n", "\n", " startup.\n", " NOUN\n", "\n", "\n", "\n", " Sundar\n", " PROPN\n", "\n", "\n", "\n", " Pichai\n", " PROPN\n", "\n", "\n", "\n", " is\n", " AUX\n", "\n", "\n", "\n", " the\n", " DET\n", "\n", "\n", "\n", " CEO\n", " PROPN\n", "\n", "\n", "\n", " of\n", " ADP\n", "\n", "\n", "\n", " Google.\n", " PROPN\n", "\n", "\n", "\n", " \n", " \n", " nsubj\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " aux\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " det\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " compound\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " dobj\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " compound\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " nsubj\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " det\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " attr\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " prep\n", " \n", " \n", "\n", "\n", "\n", " \n", " \n", " pobj\n", " \n", " \n", "\n", "" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "
\n", "\n", " Apple\n", " ORG\n", "\n", " is acquiring a \n", "\n", " U.K.\n", " GPE\n", "\n", " startup. \n", "\n", " Sundar Pichai\n", " PERSON\n", "\n", " is the CEO of \n", "\n", " Google\n", " ORG\n", "\n", ".
" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "MRkxVAsj4Cup" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "pLzSvwS44Cxb" }, "execution_count": null, "outputs": [] } ] }