TacoERE: Cluster-aware Compression for Event Relation Extraction

Yong Guan, Xiaozhi Wang, Lei Hou, Juanzi Li, Jeff Z. Pan, Jiaoyan Chen, Freddy Lecue


Abstract
Event relation extraction (ERE) is a critical and fundamental challenge for natural language processing. Existing work mainly focuses on directly modeling the entire document, which cannot effectively handle long-range dependencies and information redundancy. To address these issues, we propose a cluster-aware compression method for improving event relation extraction (TacoERE), which explores a compression-then-extraction paradigm. Specifically, we first introduce document clustering for modeling event dependencies. It splits the document into intra- and inter-clusters, where intra-clusters aim to enhance the relations within the same cluster, while inter-clusters attempt to model the related events at arbitrary distances. Secondly, we utilize cluster summarization to simplify and highlight important text content of clusters for mitigating information redundancy and event distance. We have conducted extensive experiments on both pre-trained language models, such as RoBERTa, and large language models, such as ChatGPT and GPT-4, on three ERE datasets, i.e., MAVEN-ERE, EventStoryLine and HiEve. Experimental results demonstrate that TacoERE is an effective method for ERE.
Anthology ID:
2024.lrec-main.1348
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
15511–15521
Language:
URL:
https://aclanthology.org/2024.lrec-main.1348
DOI:
Bibkey:
Cite (ACL):
Yong Guan, Xiaozhi Wang, Lei Hou, Juanzi Li, Jeff Z. Pan, Jiaoyan Chen, and Freddy Lecue. 2024. TacoERE: Cluster-aware Compression for Event Relation Extraction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15511–15521, Torino, Italia. ELRA and ICCL.
Cite (Informal):
TacoERE: Cluster-aware Compression for Event Relation Extraction (Guan et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1348.pdf