Papers by Shao Wen Tong

Copied to clipboard

Challenge:	Document-level Joint Entity and Relation Extraction benchmarks such as DocRED, Re-DocRED, and DocGNRE suffer from pervasive False Negatives (FN)
Approach:	They propose a training-free annotation pipeline that leverages user-specifiable reasoning, enriched inverse/co-occurring relation schemas, and novel entity-level constraints to address FN gaps.
Outcome:	The proposed pipeline improves on REDFM Mandarin dataset and shows that model recall scores drop on revised splits, whereas the training set mitigates this.