Papers with Open-world Relation Extraction

1 papers
Open-world Semi-supervised Generalized Relation Discovery Aligned in a Real-world Setting (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to open-world relation extraction assume that all instances of unlabeled data belong to novel classes.
Approach: They propose a method that classifies relations from known and novel classes within unlabeled data.
Outcome: The proposed method outperforms existing methods on Open-world RE benchmarks.

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