EDM3: Event Detection as Multi-task Text Generation

Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar, Kuntal Pal, Chitta Baral


Abstract
We present EDM3, a novel approach for Event Detection (ED) based on decomposing and reformulating ED, and fine-tuning over its atomic subtasks. EDM3 enhances knowledge transfer while mitigating prediction error propagation inherent in pipelined approaches. EDM3 infers dataset-specific knowledge required for the complex primary task from its atomic tasks, making it adaptable to any set of event types. We evaluate EDM3 on multiple ED datasets, achieving state-of-the-art results on RAMS (71.3% vs 65.1% F1), and competitive performance on WikiEvents, MAVEN (∆ = 0.2%), and MLEE (∆ = 1.8%). We present an ablation study over rare event types (<15 instances in training data) in MAVEN, where EDM3 achieves ~90% F1. To the best of the authors’ knowledge, we are the first to analyze ED performance over non-standard event configurations (i.e., multi-word and multi-class triggers). Experimental results show that EDM3 achieves ~90% exact match accuracy on multi-word triggers and ~61% prediction accuracy on multi-class triggers. This work establishes the effectiveness of EDM3 in enhancing performance on a complex information extraction task.
Anthology ID:
2024.starsem-1.35
Volume:
Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Danushka Bollegala, Vered Shwartz
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
438–451
Language:
URL:
https://aclanthology.org/2024.starsem-1.35
DOI:
Bibkey:
Cite (ACL):
Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar, Kuntal Pal, and Chitta Baral. 2024. EDM3: Event Detection as Multi-task Text Generation. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 438–451, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
EDM3: Event Detection as Multi-task Text Generation (Anantheswaran et al., *SEM 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.starsem-1.35.pdf