A simple/fast/accurate accent prediction for non-accented Vietnamese text

🍰 A library for creating n-grams, skip-grams, bag of words, bag of n-grams, bag of skip-grams.

KiloGram algorithm for finding the top-k most frequent n-grams for large values of n quickly with fixed memory.

English language article analyzer using some NLP techniques

Increasing the efficiency of Naïve Bayes model in NLP for Sentiment Analysis. B.Tech Final Year Project

Match movie titles with a set of reviews data and perform sentiment analysis

Big Bang Theory Series Characters classification

Recovery of ActiveWatch statistical text analysis from 20th Century Java code saved on a CD-ROM disk. This probably should be rewritten, but can now demonstrate AW mapping of dynamic text content and detection of unusual activity.

Exploring the history of word usage in English texts with a weighted popularity history plot.

a N-gram language model that can predict the next few words of a sentence based on the occurrence of the previous N words

Produces meaningful completions for partial queries given by the user. Semester project for the course "Information Retrieval" at the University of Tübingen in the winter semester 2016/17.

A java program which identifies and sums all n-grams/shingles/l-mer/k-mer of contiguus size n in a text document, then outputs the results to a file

It count each and every word in a 1-gram using mapReduce

A Java program that determines the natural language of text using n-grams