computational-linguistics

An attempt at implementing a variety of NLP programmes using Pytorch based off of the Pytorch tutorials

A simple web application

This repository contains simple tutorials for beginners who want to learn more about NLP & AI

A python package to run contextualized topic modeling for Indic Languages. indicCTMs combine contextualized embeddings (e.g., IndicBERT) with topic models to get coherent topics in Hindi, English, and Tamil.

FST-based tokenizer in modern C++ producing typed Token structs, with no external dependencies.

A computational linguistics probing study examining how pre-trained language models process Turkish-English code-switching (CS) text compared to monolingual Turkish counterparts.

Modeling and detecting patient treatment expectations from synthetic and real-world text

Explainable lexical knowledge graph: morphology, semantic decomposition, etymology and affix alignment for Telugu, Hindi, English, French and Tamil (the T.H.E.F.T. framework). No LLMs; every etymology sourced.

A Conservation Law for Commitment in Language Under Transformative Compression and Recursive Application — the foundational published law. CC-BY-4.0. Patent pending 63/877,177.

PoS tagging for Greek and Latin texts using dynamic programming and Viterbi algorithm.

A Library in development to assess syntactic complexity

Quantify the similarity between pairs of words of a dataset using Lin similarity, NPMI and LSA.

Rule-based recognition of Spanish robot commands using a feature-based grammar and semantic parsing

TS TextLab, Türkçe metinler üzerinde TS Tokenizer ve TS POSTagger ile çalışan bir masaüstü Türkçe metin analiz ve işleme uygulamasıdır.

কথার রং Kothar Rong — Open Bangla Slang Dataset: 3,318 entries / 20 categories + 505-row cross-lingual slang→Bangla reverse-mapping layer (EN/HI/UR/AR/KO/JA/ES, process-labeled) + 239K-comment usage corpus + 2,303 audio clips + usage evidence. CC BY-SA 4.0

Comparative NLP study evaluating VADER, Flair and spaCy across 152 tracks from 12 Tumblr-era albums.

Slang Identification via Machine Learning using sklearn.

Adopting a computer-assisted approach to historical language comparison: defining early steps in a Dogon languages comparative work.

A network science and computational linguistics project analyzing lexical connections between Burushaski and global languages using centrality measures and interactive graph visualizations.