djinn-anthrope / LanguageModel

NLP Assignment 1

Problem Statement

Tokenize the Gutenberg corpus, and care for the exceptions. Create a language model based on N-gram prediction. Use the language model to score a sentence by its grammatical features, including punctuation. Finally, score the spelling of a word without using a dictionary lookup.

Technology

Language The language used for this is Python3 (v 3.7.3)

The project is executed as a Jupyter Notebook

Instructions to run the program

1. Clone this repository

$ git clone https://github.com/AlokDebnath/LanguageModel.git

2. Run the following command

$ jupyter notebook Project\ 1\ Task\ 1

3. Click shift+enter at every code block