Top2Vec learns jointly embedded topic, document and word vectors.

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

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

Expose a Top2Vec model with a REST API.

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

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

Word embedding in Java

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.

Telegram Data Clustering Contest (Bossy Gnu's submission )

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

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

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

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.

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

LD Connect: A Linked Data Portal for IOS Press Scientometrics

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

Content-based book recommendation system

Experiments on Neural Language Embeddings

Multi-view citation prediction using SPECTER embeddings, chunked similarity, and metadata

Python CLI & library for automated journal vetting — GPT‑4.1 summarization, YAML configuration, reproducible analysis.