Papers by Marc P.Y. Desmulliez

1 papers
A Scientific Information Extraction Dataset for Nature Inspired Engineering (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to extract relevant biological information from scientific literature are difficult and require domain-specific knowledge.
Approach: They describe a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text.
Outcome: The proposed dataset allows for training and evaluation of Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.

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