{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Text Normalization (English)\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import spacy\n",
"import unicodedata\n",
"#from contractions import CONTRACTION_MAP\n",
"import re\n",
"from nltk.corpus import wordnet\n",
"import collections\n",
"#from textblob import Word\n",
"from nltk.tokenize.toktok import ToktokTokenizer\n",
"from bs4 import BeautifulSoup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## HTML Tags"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"b'\\n\\n\\n\\nPython (programming language) - Wikipedia\\n