A very simple framework for state-of-the-art Natural Language Processing (NLP)

A sentiment analysis project using Twitter tweet data. Project aimed to analyse and compare sentiment attached to perceived weight stigma.

Worked on creating triples for an ontology, equivalence mapping 2 ontologies and running OWL2Vec

A Fast, Adaptive, Stable, and Transferable Topic Model

Resume Matcher is an open source, free tool to improve your resume. It works by using language models to compare and rank resumes with job descriptions.

Naive RAG implementations using LangChain + llama-index + OpenAI + GradientAI + Sentence_Transformer + Nomic AI + FAISS and more

Analysis of Roget's Thesaurus lexicon, using web scraping and machine learning techniques

Algorithmic solvers for popular NYT word puzzles

Topic Modelling for Humans

Deep learning for natural language processing

Developed a deep learning model utilizing TensorFlow to automate the classification of financial documents. Leveraging a Bidirectional LSTM RNN, we accurately categorize the documents. Our user-friendly Streamlit application ensures high accuracy & efficiency in document management, all deployed on the Hugging Face platform for seamless integration

This repository contains the code for the Transformer-Representation Neural Topic Model (TNTM) based on the paper "Probabilistic Topic Modelling with Transformer Representations" by Arik Reuter, Anton Thielmann, Christoph Weisser, Benjamin Säfken and Thomas Kneib

The code powering searchthearxiv.com, a simple semantic search engine for more than 300,000 ML papers on arXiv.

DSC 214 Topological Data Science Project

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions

Improving Word Translation via Two-Stage Contrastive Learning (ACL 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

front end to greek and latin corpora: searching, browsing, concordances, texts, dictionaries, parsing

This repository provides a complete workflow for text processing using Hugging Face Transformers and NLTK. It includes modules for sentence normalization, spelling correction, word embedding generation, positional encoding computation, and English-to-French translation

Toolkit to obtain and preprocess German text corpora, train models and evaluate them with generated testsets. Built with Gensim and Tensorflow.

Code implementation for our DAS, 2020 paper titled "Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval"