The reviewed record of science sign in
Pith

arxiv: 2310.15470 · v1 · pith:E4TJKDB4 · submitted 2023-10-24 · cs.CL · cs.LG

Continual Event Extraction with Semantic Confusion Rectification

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:E4TJKDB4record.jsonopen to challenge →

classification cs.CL cs.LG
keywords eventtypesconfusionsemanticcontinualextractionmodelrectification
0
0 comments X
read the original abstract

We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting. We observe that the semantic confusion on event types stems from the annotations of the same text being updated over time. The imbalance between event types even aggravates this issue. This paper proposes a novel continual event extraction model with semantic confusion rectification. We mark pseudo labels for each sentence to alleviate semantic confusion. We transfer pivotal knowledge between current and previous models to enhance the understanding of event types. Moreover, we encourage the model to focus on the semantics of long-tailed event types by leveraging other associated types. Experimental results show that our model outperforms state-of-the-art baselines and is proficient in imbalanced datasets.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.