Lune

ACL Findings2025

GEMS: Generation-Based Event Argument Extraction via Multi-perspective Prompts and Ontology Steering

Run Lin, Yao Liu, Yanglei Gan, Yuxiang Cai, Tian Lan, Qiao Liu

Abstract

Generative methods significantly advance event argument extraction by probabilistically generating event argument sequences in a structured format. However, existing approaches primarily rely on a single prompt to generate event arguments in a fixed, predetermined order. Such a rigid approach overlooks the complex structural and dynamic interdependencies among event arguments. In this work, we present GEMS, a multi-prompt learning framework that Generates Event arguments via Multi-perspective prompts and ontology Steering. Specifically, GEMS utilizes multiple unfilled prompts for each sentence, predicting event arguments in varying sequences to explicitly capture the interrelationships between arguments. These predictions are subsequently aggregated using a voting mechanism. Furthermore, an ontologydriven steering mechanism is proposed to ensure that the generated arguments are contextually appropriate and consistent with eventspecific knowledge. Extensive experiments on two benchmark datasets demonstrate that GEMS achieves state-of-the-art performance, particularly in low-resource settings. The source code is available at: https://github. com/AONE-NLP/EAE-GEMS.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Event Extraction as Machine Reading Comprehension cites Event Extraction by Answering (Almost) Natural Questions
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NERAhmed Ewais, Ahmed Hashish, Amr AliACL 2026

Builds on24

  1. Event Extraction by Answering (Almost) Natural QuestionsXinya Du, Claire CardieEMNLP 2020 · 391 citations
  2. A Joint Neural Model for Information Extraction with Global FeaturesYing Lin, Heng Ji, Fei Huang, Lingfei WuACL 2020 · 376 citations
  3. Self-regulating Prompts: Foundational Model Adaptation without ForgettingMuhammad Uzair Khattak, Syed Talal Wasim, Muzammal Naseer, Salman Khan et al.ICCV 2023 · 365 citations
  4. Event Extraction as Machine Reading ComprehensionJian Liu, Yubo Chen, Kang Liu, Wei Bi et al.EMNLP 2020 · 300 citations
  5. Inducing Relational Knowledge from BERTZied Bouraoui, José Camacho-Collados, Steven SchockaertAAAI 2020 · 183 citations

Related papers

  1. Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument ExtractionWanlong Liu, Li Zhou, Dingyi Zeng, Yichen Xiao et al.ACL Findings 2024 · 27 citations
  2. Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument ExtractionYubo Ma, Zehao Wang, Yixin Cao, Mukai Li et al.ACL 2022 · 182 citations
  3. Revisiting Event Argument Extraction: Can EAE Models Learn Better When Being Aware of Event Co-occurrences?Yuxin He, Jingyue Hu, Buzhou TangACL 2023 · 26 citations
  4. Contextualized Soft Prompts for Extraction of Event ArgumentsChien Van Nguyen, Hieu Man, Thien Huu NguyenACL Findings 2023 · 20 citations
  5. Few-Shot Document-Level Event Argument ExtractionXianjun Yang, Yujie Lu, Linda R. PetzoldACL 2023 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines