machine-translation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: nltk in c:\\users\\daniil_ekzarian\\appdata\\local\\programs\\python\\python37-32\\lib\\site-packages (3.4)\n",
      "Requirement already satisfied: six in c:\\users\\daniil_ekzarian\\appdata\\roaming\\python\\python37\\site-packages (from nltk) (1.12.0)\n",
      "Requirement already satisfied: singledispatch in c:\\users\\daniil_ekzarian\\appdata\\local\\programs\\python\\python37-32\\lib\\site-packages (from nltk) (3.4.0.3)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "You are using pip version 18.1, however version 19.0.3 is available.\n",
      "You should consider upgrading via the 'python -m pip install --upgrade pip' command.\n",
      "[nltk_data] Downloading package comtrans to\n",
      "[nltk_data]     C:\\Users\\Daniil_Ekzarian\\AppData\\Roaming\\nltk_data...\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import sys\n",
    "!{sys.executable} -m pip install nltk\n",
    "\n",
    "import nltk\n",
    "nltk.download('comtrans')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['klein', 'ist', 'das', 'Haus']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk.translate import AlignedSent, Alignment\n",
    "algnsent = AlignedSent(['klein', 'ist', 'das', 'Haus'],\n",
    "     ['the', 'house', 'is', 'small'], Alignment.fromstring('0-3 1-2 2-0 3-1'))\n",
    "algnsent.words"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['the', 'house', 'is', 'small']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "algnsent.mots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Alignment([(0, 3), (1, 2), (2, 0), (3, 1)])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "algnsent.alignment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<AlignedSent: 'Weshalb also sollten...' -> 'So why should EU arm...'>\n",
      "0-0 0-1 1-0 2-2 3-4 3-5 4-7 5-8 6-3 7-9 8-9 9-10 9-11 10-12 11-6 12-6 13-13\n"
     ]
    }
   ],
   "source": [
    "from nltk.corpus import comtrans\n",
    "print(comtrans.aligned_sents()[54])\n",
    "print(comtrans.aligned_sents()[54].alignment)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}