Next-token prediction in JavaScript — build fast language and diffusion models.

Python implementation of an N-gram language model with Laplace smoothing and sentence generation.

Ngrams with Basic Smoothings

A C++ library implementing fast language models estimation using the 1-Sort algorithm.

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.

Built a system from scratch in Python which can detect spelling and grammatical errors in a word and sentence respectively using N-gram based Smoothed-Language Model, Levenshtein Distance, Hidden Markov Model and Naive Bayes Classifier.

A general emoji-text translator which translates emoji-text to chinese

Programming for NLP Project - Implement a basic n-gram language model and generate sentence using beam search

Slides, exercises, and exams for my course "Natural Language Processing" (École Pour l'Informatique et les Techniques Avancées, 2024 and 2025)

Ngrams with Basic Smoothings

It's a python based n-gram langauage model which calculates bigrams, probability and smooth probability (laplace) of a sentence using bi-gram and perplexity of the model.

Language identification toolkit for identifying what language a document is writen in

Ngrams with Basic Smoothings

Ngrams with Basic Smoothings

N-Gram language model that learns n-gram probabilities from a given corpus and generates new sentences from it based on the conditional probabilities from the generated words and phrases.

Ngram language model implemented in Pharo

Python implementation of n-gram language models from scratch and using NLTK (+ slides from my NLP course)

NLP-persian-poet-identification

Language identifier with using ngram language model

Academic project centered around n-grams and their application in developing a spelling corrector with contextual awareness.