A Chrome extension to provide semantic search over your browsing history.

(NeurIPS 2024) A Fast, Adaptive, Stable, and Transferable Topic Model

Top2Vec learns jointly embedded topic, document and word vectors.

Medical Retrieval-Augmented Generation (RAG) Knowledge Base - A Next.js and LangChain-powered app that processes and stores medical documents as vector embeddings in Pinecone for efficient similarity search.

This Streamlit application demonstrates the integration of ChatGroq (Llama3 model), OpenAIEmbeddings, and FAISS for document embedding and retrieval.

🍊 PAUSE (Positive and Annealed Unlabeled Sentence Embedding), accepted by EMNLP'2021 🌴

Dive into the world of Word2Vec and Doc2Vec models to uncover insights and applications.

We address the task of learning contextualized word, sentence and document representations with a hierarchical language model by stacking Transformer-based encoders on a sentence level and subsequently on a document level and performing masked token prediction.

Document chatbot — multiple files, topics, chat windows and chat history. Powered by GPT.

Content-based book recommendation system

Expose a Top2Vec model with a REST API.

LD Connect: A Linked Data Portal for IOS Press Scientometrics

Word embedding in Java

Telegram Data Clustering Contest (Bossy Gnu's submission )

Applying NLP to understand people's sentiment about Covid-19 and Government actions in Italy, conditional on their political affiliation.

Improving document embedding with weighted average of word embedding through topic modeling

An open-source framework to create and test document embeddings using topic models.

Container-first, JSON-configurable, NLP REST service based on Flair

Experiments on Neural Language Embeddings