/BiGram-modelling

Creates bigram model of a given corpus

Primary LanguageJava

N-grams is an important concept in Natural Language Processing as it has several important applicaions like sentence completion. In this project I have calculated a Bigram Probability model of a corpus.

3 output files containing calculations of bigram probabilities will be generated on running the program,
1) No smoothing is done
2) Add one Laplace Smoothing is done
3) Good Turing Smoothing is done


How to run:
---Java 8 required

Compile : open cmd in current directory and type : javac BigramProbabilities.java

Run: java BigramProbabilities <File Name>
eg - java BigramProbabilities NLPCorpusTreebank.txt