question_answering.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Question Answering in English"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "question_answering = pipeline(\"question-answering\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "context = \"\"\"Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as \"training data\", in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "question = \"What are machine learning models based on?\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/raymond/.conda/envs/movie_script_generation/lib/python3.6/site-packages/transformers/tokenization_utils_base.py:1423: FutureWarning: The `max_len` attribute has been deprecated and will be removed in a future version, use `model_max_length` instead.\n",
      "  FutureWarning,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Answer: sample data,\n",
      "Score: 0.8846667408943176\n"
     ]
    }
   ],
   "source": [
    "result = question_answering(question=question, context=context)\n",
    "\n",
    "print(\"Answer:\", result['answer'])\n",
    "print(\"Score:\", result['score'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Question Answering in Another Language Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "question_answering = pipeline(\"question-answering\", model=\"mrm8488/bert-multi-cased-finetuned-xquadv1\",\n",
    "    tokenizer=\"mrm8488/bert-multi-cased-finetuned-xquadv1\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/raymond/.conda/envs/movie_script_generation/lib/python3.6/site-packages/transformers/tokenization_utils_base.py:1423: FutureWarning: The `max_len` attribute has been deprecated and will be removed in a future version, use `model_max_length` instead.\n",
      "  FutureWarning,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Answer: 机器学习是人工智能的一个分支。\n",
      "Score: 0.9717233777046204\n"
     ]
    }
   ],
   "source": [
    "context = \"\"\"机器学习是人工智能的一个分支。 是个人很热门的专业。\"\"\"\n",
    "question = \"机器学习是什么的分支？\"\n",
    "\n",
    "result = question_answering(question=question, context=context)\n",
    "\n",
    "print(\"Answer:\", result['answer'])\n",
    "print(\"Score:\", result['score'])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}