/typo_dict

A Dictionary of Common Typos and Corresponding Corrections in Social Media

Primary LanguagePython

typo_dict

Typos or common abbrebations (e.g., 'luv'->'love', 'gr8'->'great') are very common in social media such as Facebook, Twitter and Whatsapp. It hinders NL parsers to recognize the syntax and brings many challenges in natural language processing.

This project aims to manually summarize a dictionary of common typos and corresponding corrections.

Usage

1. Clone the repository

$ git clone https://github.com/guxd/typo_dict.git

File Introduction

  1. typos_en_social.py Typos in social media, e.g., Twitter, Facebook, Whatsapp

  2. typos_en_program.py Typos in programming environment, e.g., StackOverflow