Experiments on Neural Language Embeddings

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

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

Expose a Top2Vec model with a REST API.

Content-based book recommendation system

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

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

Top2Vec learns jointly embedded topic, document and word vectors.

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

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

Korean R&D document pipeline for patents, grants, papers, and PDFs with KSS-based preprocessing, KoSentenceBERT embeddings, and Qdrant semantic search via FastAPI.