UoL/CM3060 Natural Language Processing/Week 3/2.2.1 Sentence segmentation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1878fa45-3b4a-44f5-b5fa-97c00adb4593",
   "metadata": {},
   "source": [
    "# Sentence segmentation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "aff71edc-bb8f-49dc-a4fd-bbac1a74ebed",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3708c40d-cb73-4a6e-96ad-6d6e70c862ff",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to C:\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nltk.download('punkt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "bd55a5f7-ff62-47b8-928b-d5b60b92e9f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = '''Punctuation denotes the end of a sentence!\n",
    "“But not always!”, said Fred... (who is a professor).\n",
    "Some sentences could break over multiple lines\n",
    "and begin with a lower case letter.\n",
    "a1 could be a variable name.\n",
    "'''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5fd18291-2765-4841-9cdf-4efbe110bded",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Punctuation denotes the end of a sentence!\\n“But not always!”, said Fred... (who is a professor).\\nSome sentences could break over multiple lines\\nand begin with a lower case letter.\\na1 could be a variable name.\\n'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2a010ec4-c5ad-4429-be04-7f3626d3a6e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "sents = nltk.sent_tokenize(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "74e585c9-a137-4008-824d-699dcb470943",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'“But not always!”, said Fred... (who is a professor).'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sents[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "815c6f21-4c1f-491a-96cf-b6ba6878eb67",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(sents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6c895aea-7fc0-47f0-a9ca-6710735da51a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Punctuation denotes the end of a sentence!\n",
      "“But not always!”, said Fred... (who is a professor).\n",
      "Some sentences could break over multiple lines\n",
      "and begin with a lower case letter.\n",
      "a1 could be a variable name.\n"
     ]
    }
   ],
   "source": [
    "for s in sents:\n",
    "    print(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "82da27f5-4ad0-4ec5-a20f-e83646a60fc4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Punctuation denotes the end of a sentence!\n",
      "---\n",
      "“But not always!”, said Fred... (who is a professor).\n",
      "---\n",
      "Some sentences could break over multiple lines\n",
      "and begin with a lower case letter.\n",
      "---\n",
      "a1 could be a variable name.\n"
     ]
    }
   ],
   "source": [
    "print('\\n---\\n'.join(sents))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "aecb0078-42ae-432a-8fc5-3f1cd9baa5db",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4\n",
      "\n",
      "Punctuation denotes the end of a sentence!\n",
      "“But not always!”, said Fred... (who is a professor).\n",
      "Some sentences could break over multiple lines\n",
      "and begin with a lower case letter.\n",
      "a1 could be a variable name.\n"
     ]
    }
   ],
   "source": [
    "text = '''Punctuation denotes the end of a sentence!\n",
    "“But not always!”, said Fred... (who is a professor).\n",
    "Some sentences could break over multiple lines\n",
    "and begin with a lower case letter.\n",
    "a1 could be a variable name.\n",
    "'''\n",
    "sents = nltk.sent_tokenize(text)\n",
    "print(len(sents))\n",
    "print()\n",
    "for s in sents:\n",
    "    print(s)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}