Papers by Viggo Unmack Gascou

1 papers
How to Encode Domain Information in Relation Classification (2024.lrec-main)

Copied to clipboard

Challenge: Existing deep learning models require a lot of training data to obtain high performance.
Approach: They propose a multi-domain training setup for Relation Classification (RC) they compare different ways to enrich input instances with domain information .
Outcome: The proposed model improves > 2 Macro-F1 against the baseline setup.

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