Lune

ACL Findings2024

Scented-EAE: Stage-Customized Entity Type Embedding for Event Argument Extraction

Yu Yang, Jinyu Guo, Kai Shuang, Chenrui Mao

Abstract

Existing methods for incorporating entities into EAE rely on prompts or NER. They typically fail to explicitly explore the role of entity types, which results in shallow argument comprehension and often encounter three issues: (1) weak semantic associations due to missing roleentity correspondence cues; (2) compromised semantic integrity from abandoning context after recognizing entities regardless of their types;

(3) one-sided semantic understanding relying solely on argument role semantics. To tackle these issues, we propose Scented-EAE, an EAE model with stage-customized entity type embedding to explicitly underscore and explore the role of entity types, thus intervening in argument selection. Specifically, at the input stage, we strengthen semantic associations by prompting role-entity correspondence after extending a non-autoregressive decoder as part of the encoder. At the intermediate stage, we preserve semantic integrity by optimizing our proposed BIO-aware NER and EAE via a novel IPE joint learning. At the output stage, we expand semantic understanding dimensions by determining arguments using span selectors from argument roles and entity types. Experiments show that our model achieves state-of-the-art performance on mainstream benchmarks. In addition, it also exhibits robustness in low-resource settings with the help of prompts and entity types. 1

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

  • Dynamic Prefix-Tuning for Generative Template-based Event Extraction cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Dynamic Prefix-Tuning for Generative Template-based Event Extraction cites Event Extraction by Answering (Almost) Natural Questions
  • Dynamic Prefix-Tuning for Generative Template-based Event Extraction cites A Joint Neural Model for Information Extraction with Global Features
  • EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain cites Event Extraction by Answering (Almost) Natural Questions
  • EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain cites Dynamic Prefix-Tuning for Generative Template-based Event Extraction
  • EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain cites Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
  • EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain cites A Joint Neural Model for Information Extraction with Global Features
  • Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction cites Event Extraction by Answering (Almost) Natural Questions
  • Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction cites A Joint Neural Model for Information Extraction with Global Features
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific DomainYi-Fan Lu, Xian-Ling Mao, Bo Wang, Xiao Liu et al.ACL 2026 · 1 citation

Builds on21

  1. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  2. Event Extraction by Answering (Almost) Natural QuestionsXinya Du, Claire CardieEMNLP 2020 · 391 citations
  3. A Joint Neural Model for Information Extraction with Global FeaturesYing Lin, Heng Ji, Fei Huang, Lingfei WuACL 2020 · 376 citations
  4. Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument ExtractionYubo Ma, Zehao Wang, Yixin Cao, Mukai Li et al.ACL 2022 · 182 citations
  5. Dynamic Prefix-Tuning for Generative Template-based Event ExtractionXiao Liu, Heyan Huang, Ge Shi, Bo WangACL 2022 · 120 citations

Related papers

  1. Contextualized Soft Prompts for Extraction of Event ArgumentsChien Van Nguyen, Hieu Man, Thien Huu NguyenACL Findings 2023 · 20 citations
  2. REAR: Reinforced Reasoning Optimization for Event Argument Extraction with Relation-Aware SupportJianwen Luo, Yu Hong, Shuai Yang, Jianmin YaoEMNLP Findings 2025
  3. Bi-Directional Iterative Prompt-Tuning for Event Argument ExtractionLu Dai, Bang Wang, Wei Xiang, Yijun MoEMNLP 2022 · 20 citations
  4. Improving Entity Linking by Modeling Latent Entity Type InformationShuang Chen, Jinpeng Wang, Feng Jiang, Chin-Yew LinAAAI 2020 · 71 citations
  5. Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent DecoderXiangyu Xi, Wei Ye, Shikun Zhang, Quanxiu Wang et al.ACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines