← Search

Italo Luis Da Silva

1 accepted papers

2024

Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems

EMNLP 2024main

The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to approximate human evaluation, achieving high agreement. We used…