translator_wp_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "sudden-surprise",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from bpemb import BPEmb\n",
    "\n",
    "# You load BPEmb model for each language.\n",
    "bpemb_de = BPEmb(lang='de', vs=10000, dim=100)\n",
    "bpemb_en = BPEmb(lang='en', vs=10000, dim=100)\n",
    "bpemb_ja = BPEmb(lang='ja', vs=10000, dim=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "confused-there",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[386, 9937, 9927, 7, 491, 272, 305, 3838, 5447, 819, 26, 7, 1645, 9935]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Let's see how the sentences in three different languages are encoded into integer are decoded. \n",
    "\n",
    "# Encoding in English.\n",
    "bpemb_en.encode_ids(\"I'm the only one who cannot speak German in the office.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "developmental-cleveland",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[3077,\n",
       " 4725,\n",
       " 26,\n",
       " 3478,\n",
       " 39,\n",
       " 131,\n",
       " 4969,\n",
       " 9927,\n",
       " 9940,\n",
       " 26,\n",
       " 1502,\n",
       " 250,\n",
       " 7690,\n",
       " 713,\n",
       " 9935]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Encoding in German. \n",
    "bpemb_de.encode_ids(\"Ich bin der Einzige in dem Büro, der kein Deutsch sprechen kann.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "distinguished-small",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[2025,\n",
       " 4406,\n",
       " 6056,\n",
       " 6047,\n",
       " 421,\n",
       " 6310,\n",
       " 6049,\n",
       " 6406,\n",
       " 6234,\n",
       " 41,\n",
       " 382,\n",
       " 6988,\n",
       " 1755,\n",
       " 6085,\n",
       " 6037]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Encoding in Japanese. \n",
    "bpemb_ja.encode_ids(\"そのオフィスでドイツ語が話せないのは私だけです。\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "prostate-ballot",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "i'm the only one who cannot speak german in the office.\n",
      "ich bin der einzige in dem büro, der kein deutsch sprechen kann.\n",
      "そのオフィスでドイツ語が話せないのは私だけです。\n"
     ]
    }
   ],
   "source": [
    "# The encoded sentences can be conversely decoded into the original languages with few changes. \n",
    "print( bpemb_en.decode_ids([386, 9937, 9927, 7, 491, 272, 305, 3838, 5447, 819, 26, 7, 1645, 9935]) )\n",
    "print( bpemb_de.decode_ids([3077, 4725, 26, 3478, 39, 131, 4969, 9927, 9940, 26, 1502, 250, 7690, 713, 9935]) )\n",
    "print( bpemb_ja.decode_ids([2025, 4406, 6056, 6047, 421, 6310, 6049, 6406, 6234, 41, 382, 6988, 1755, 6085, 6037]) )"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}