Speakers
Description
Research groups in the humanities generate a substantial number of publications, contributing to an ever-expanding body of scholarly work. When a scholar is interested in the topics covered or has specific questions about (subsets of) publications, they must overcome the big number of publications to read. We demonstrate the use of language models in the humanities by showcasing two applications: First, the usage of Latent Dirichlet Allocation for identification of topics with minimal effort. Second, a new chatbot ChatHA for answering questions about documents. ChatHA also provides citations which excerpts from documents it uses. On the technical side, ChatHA is the extension of pretrained language models with a set of documents using RAG. Citations are generated by postprocessing the answer.
| I want to give a Lightning Talk | no |
|---|
