6.Parts of Speech & Meaning.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Parts of Speech and Meaning (English Only)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "t = \"Cyprus, officially the Republic of Cyprus, is an island country in the Eastern Mediterranean and the third largest and third most populous island in the Mediterranean. Cyprus is located south of Turkey, west of Syria and Lebanon, northwest of Israel, north of Egypt, and southeast of Greece. Cyprus is a major tourist destination in the Mediterranean. With an advanced, high-income economy and a very high Human Development Index, the Republic of Cyprus has been a member of the Commonwealth since 1961 and was a founding member of the Non-Aligned Movement until it joined the European Union on 1 May 2004. On 1 January 2008, the Republic of Cyprus joined the eurozone.\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Tokenization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['cyprus, officially the republic of cyprus, is an island country in the eastern mediterranean and the third largest and third most populous island in the mediterranean.',\n",
       " 'cyprus is located south of turkey, west of syria and lebanon, northwest of israel, north of egypt, and southeast of greece.',\n",
       " 'cyprus is a major tourist destination in the mediterranean.',\n",
       " 'with an advanced, high-income economy and a very high human development index, the republic of cyprus has been a member of the commonwealth since 1961 and was a founding member of the non-aligned movement until it joined the european union on 1 may 2004. on 1 january 2008, the republic of cyprus joined the eurozone.']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk import sent_tokenize, word_tokenize\n",
    "sentences = sent_tokenize(t.lower())\n",
    "sentences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['cyprus',\n",
       " 'is',\n",
       " 'a',\n",
       " 'major',\n",
       " 'tourist',\n",
       " 'destination',\n",
       " 'in',\n",
       " 'the',\n",
       " 'mediterranean',\n",
       " '.']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokens = word_tokenize(sentences[2])\n",
    "tokens"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. POS Tagging"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('cyprus', 'NN'),\n",
       " ('is', 'VBZ'),\n",
       " ('a', 'DT'),\n",
       " ('major', 'JJ'),\n",
       " ('tourist', 'NN'),\n",
       " ('destination', 'NN'),\n",
       " ('in', 'IN'),\n",
       " ('the', 'DT'),\n",
       " ('mediterranean', 'NN'),\n",
       " ('.', '.')]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk import pos_tag\n",
    "tags = pos_tag(tokens)\n",
    "tags"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To access documentation for tags, for example for `NN`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "NN: noun, common, singular or mass\n",
      "    common-carrier cabbage knuckle-duster Casino afghan shed thermostat\n",
      "    investment slide humour falloff slick wind hyena override subhumanity\n",
      "    machinist ...\n"
     ]
    }
   ],
   "source": [
    "import nltk.help\n",
    "nltk.help.upenn_tagset('NN')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Word senses (for homonyms)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "WordNet is a lexical database for the English language in the form of a semantic graph. \n",
    "\n",
    "WordNet groups English words into sets of synonyms called synsets, provides short definitions and usage examples, and records a number of relations among these synonym sets or their members.\n",
    "\n",
    "NLTK provides an interface to the WordNet API."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Synset('homo.n.02'),\n",
       " Synset('human.a.01'),\n",
       " Synset('human.a.02'),\n",
       " Synset('human.a.03')]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk.corpus import wordnet as wn\n",
    "wn.synsets('human')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'any living or extinct member of the family Hominidae characterized by superior intelligence, articulate speech, and erect carriage'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wn.synsets('human')[0].definition()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'characteristic of humanity'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wn.synsets('human')[1].definition()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Synset('homo.n.02')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "human = wn.synsets('Human', pos=wn.NOUN)[0]\n",
    "human"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Synset('hominid.n.01')]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "human.hypernyms() # A hypernym is a word with a broad meaning constituting a category into which words with more specific meanings fall; a superordinate. For example, colour is a hypernym of red."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Synset('homo_erectus.n.01'),\n",
       " Synset('homo_habilis.n.01'),\n",
       " Synset('homo_sapiens.n.01'),\n",
       " Synset('homo_soloensis.n.01'),\n",
       " Synset('neandertal_man.n.01'),\n",
       " Synset('rhodesian_man.n.01'),\n",
       " Synset('world.n.08')]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "human.hyponyms()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Synset('bicycle.n.01')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bike = wn.synsets('bicycle')[0]\n",
    "bike"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Synset('female_child.n.01')"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "girl = wn.synsets('girl')[1]\n",
    "girl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.34782608695652173"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bike.wup_similarity(human) # The Wu-Palmer metric (WUP) is a measure of similarity based on distance in the graph. There are many other metrics too."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5217391304347826"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "girl.wup_similarity(human)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['girl',\n",
       " 'miss',\n",
       " 'missy',\n",
       " 'young_lady',\n",
       " 'young_woman',\n",
       " 'fille',\n",
       " 'female_child',\n",
       " 'girl',\n",
       " 'little_girl',\n",
       " 'daughter',\n",
       " 'girl',\n",
       " 'girlfriend',\n",
       " 'girl',\n",
       " 'lady_friend',\n",
       " 'girl']"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "synonyms = []\n",
    "for syn in wn.synsets('girl'):\n",
    "    for lemma in syn.lemmas(): #  A lemma is basically the dictionary form or base form of a word, as opposed to the various inflected forms of a word. \n",
    "        synonyms.append(lemma.name())\n",
    "synonyms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['male_child', 'boy', 'son', 'boy']"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "antonyms = []\n",
    "for syn in wn.synsets(\"girl\"):\n",
    "    for l in syn.lemmas():\n",
    "        if l.antonyms():\n",
    "            antonyms.append(l.antonyms()[0].name())\n",
    "antonyms"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. Chunking and Entity Recognition"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The goal of chunking is to divide a sentence into chunks. Usually each chunk contains a **head** and optionally additionally words and modifiers. Examples of chunks include noun groups and verb groups."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4.1. Chunking"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from nltk.chunk import RegexpParser"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In order to create a chunker, we need to first define a **chunk grammar**, consisting of rules that indicate how sentences should be chunked. \n",
    "\n",
    "We can define a simple grammar for a noun phrase (NP) chunker with a single regular-expression rule. This rule says that an NP chunk should be formed whenever the chunker finds an optional determiner (`DT`) followed by any number of adjectives (`JJ`) and then a noun (`NN`).\n",
    "\n",
    "Note how grammatical structures which are not noun phrases are not chunked, which is totally fine:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "grammar = \"NP: {<DT>?<JJ>*<NN>}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "Tree('S', [Tree('NP', [('cyprus', 'NN')]), ('is', 'VBZ'), Tree('NP', [('a', 'DT'), ('major', 'JJ'), ('tourist', 'NN')]), Tree('NP', [('destination', 'NN')]), ('in', 'IN'), Tree('NP', [('the', 'DT'), ('mediterranean', 'NN')]), ('.', '.')])"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chunker = RegexpParser(grammar)\n",
    "result = chunker.parse(tags)\n",
    "result"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4.2. Entity Recognition"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The goal of entity recogintion is to detect entities such as Person, Location, Time, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "Tree('S', [('cyprus', 'NN'), ('is', 'VBZ'), ('a', 'DT'), ('major', 'JJ'), ('tourist', 'NN'), ('destination', 'NN'), ('in', 'IN'), ('the', 'DT'), ('mediterranean', 'NN'), ('.', '.')])"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk.chunk import ne_chunk # ne = named entity\n",
    "ne_chunk(tags)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note `ne_chunk` was unable to detect any entities in our sentence. That is because it is quite limited, being able to recognize only the following entities: \n",
    "> FACILITY, GPE (Geo-Political Entity), GSP (Geo-Socio-Political group), LOCATION, ORGANIZATION, PERSON "
   ]
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}