bobxwu/FASTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

TopicGPT: A Prompt-Based Framework for Topic Modeling [NAACL'24]

An implementation of latent Dirichlet allocation in javascript

Fast State-of-the-Art Static Embeddings

Late Interaction Models Training & Retrieval

State-of-the-Art Embeddings, Retrieval, and Reranking

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Interpret text data with LLMs (sklearn compatible).

Carrot2: Text Clustering Algorithms and Applications