Four word embedding models implemented in Python. Supporting arbitrary context features

Tool for performing basic text analysis on the CBETA corpus

N-Gram Graph: Simple Unsupervised Representation for Graphs, NeurIPS'19 (https://arxiv.org/abs/1806.09206)

[EMNLP 2020] Keep CALM and Explore: Language Models for Action Generation in Text-based Games

This project is an auto-filling text program implemented in Python using N-gram models. The program suggests the next word based on the input given by the user. It utilizes N-gram models, specifically Trigrams and Bigrams, to generate predictions.

Comparison among four spelling correction methods. n-gram, Levenshtein, Jaro, Jaro_winkler

Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch

StrainIQ is an n-gram based method to identify and quantify microbial communities in metagenomics samples.

ngram-keylogger: typing stats that don't leak passwords

A web service that exposes semantic similarity search via a web GUI and a RESTful API.

Perspectives in computational social research term project that utilizes text analysis and predictive model to uncover the motivation for solo travel

Training repo for Toy GPT: bigram model + small domain corpus (010_llm_glossary.txt)

Training repo for Toy GPT: unigram + small neutral corpus (000_cat_dog.txt)

Parser and histogram plotter for n-gram occurrences

A pattern-recognition based Python bot that plays Rock Paper Scissors using an adaptive n-gram strategy. Built to outsmart four custom AI opponents.

n-gram language model.

A statistical 5-gram language model implemented in Python, trained on Sherlock Holmes stories by Arthur Conan Doyle (Project Gutenberg) to generate text in the author’s writing style.

A fluency_based evaluation tool for Chinese Grammatical Error Correction (CGEC)

Training repo for Toy GPT: bigram model + small structured corpus (001_animals.txt)

This Python-based SMS spam classifier utilizes the SMS Spam Collection dataset to train a Naive Bayes classifier. It demonstrates text preprocessing, feature extraction, and scikit-learn's classification capabilities.This was done under the guidance of Prof. Dr.-Ing. Milan Gnjatovic