Papers by Miguel Freire

1 papers
LumberChunker: Long-Form Narrative Document Segmentation (2024.findings-emnlp)

Copied to clipboard

Challenge: Modern NLP tasks rely on dense retrieval methods to access up-to-date and relevant contextual information.
Approach: They propose a method that leverages an LLM to dynamically segment documents by iterating on a set of sequential passages to identify the point where the content begins to shift.
Outcome: The proposed method outperforms the most competitive baseline by 7.37% in retrieval performance and integrates into a RAG pipeline.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations