Utilizing Contextual Clues and Role Correlations for Enhancing Document-Level Event Argument Extraction
- 1 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 3932-3947
Abstract
Document-level event argument extraction is a crucial yet challenging task within the field of information extraction. Current mainstream approaches primarily focus on the information interaction between event triggers and their arguments, facing two limitations: insufficient context interaction and the ignorance of event correlations. Here, we introduce a novel framework named CARG (Contextual Aggregation of Clues and Role-based Latent Guidance), comprising two innovative components: the Contextual Clues Aggregation (CCA) and the Role-based Latent Information Guidance (RLIG) 1 The CCA module leverages the attention weights derived from a pretrained encoder to adaptively assimilate broader contextual information, while the RLIG module aims to capture the semantic correlations among event roles. We then instantiate the CARG framework into two variants based on two types of mainstream EAE approaches. Notably, our CARG framework introduces less than 1% new parameters yet significantly improves the performance. Comprehensive experiments across the RAMS, WikiEvents, MLEE and ACE 2005 datasets confirm the superiority of CARG, showing significant superiority in terms of both performance and inference speed compared to major benchmarks. Further analyses demonstrate the effectiveness of the proposed modules.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U22B2061)
This publication has 72 references indexed in Scilit:
- Large language models for generative information extraction: a surveyFrontiers of Computer Science, 2024
- EIGP: document-level event argument extraction with information enhancement generated based on promptsKnowledge and Information Systems, 2024
- Making recommender systems forget: Learning and unlearning for erasable recommendationKnowledge-Based Systems, 2023
- EACE: A document-level event argument extraction model with argument constraint enhancementInformation Processing & Management, 2023
- Mutually improved response generation and dialogue summarization for multi-domain task-oriented dialogue systemsKnowledge-Based Systems, 2023
- Extensive evaluation of transformer-based architectures for adverse drug events extractionKnowledge-Based Systems, 2023
- Multi-view entity type overdependency reduction for event argument extractionKnowledge-Based Systems, 2023
- Explainable document-level event extraction via back-tracing to sentence-level event cluesKnowledge-Based Systems, 2022
- End-to-End Object Detection with Transformers2020
- Diagnostic Prediction with Sequence-of-sets Representation Learning for Clinical Events2020