Lune

ACL Findings2023

Learning from a Friend: Improving Event Extraction via Self-Training with Feedback from Abstract Meaning Representation

Zhiyang Xu, Jay Yoon Lee, Lifu Huang

Abstract

Data scarcity has been the main factor that hinders the progress of event extraction. To overcome this issue, we propose a Self-Training with Feedback (STF) framework that leverages the large-scale unlabeled data and acquires feedback for each new event prediction from the unlabeled data by comparing it to the Abstract Meaning Representation (AMR) graph of the same sentence. Specifically, STF consists of (1) a base event extraction model trained on existing event annotations and then applied to large-scale unlabeled corpora to predict new event mentions as pseudo training samples, and (2) a novel scoring model that takes in each new predicted event trigger, an argument, its argument role, as well as their paths in the AMR graph to estimate a compatibility score indicating the correctness of the pseudo label. The compatibility scores further act as feedback to encourage or discourage the model learning on the pseudo labels during self-training. Experimental results on three benchmark datasets, including ACE05-E, ACE05-E + , and ERE, demonstrate the effectiveness of the STF framework on event extraction, especially event argument extraction, with significant performance gain over the base event extraction models and strong baselines. Our experimental analysis further shows that STF is a generic framework as it can be applied to improve most, if not all, event extraction models by leveraging largescale unlabeled data, even when high-quality AMR graph annotations are not available. 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.

3 top-tier papers have 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

  • Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding cites Event Extraction by Answering (Almost) Natural Questions
  • Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding 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 papers3

  1. Enhancing Uncertainty Modeling with Semantic Graph for Hallucination DetectionKedi Chen, Qin Chen, Jie Zhou, Xinqi Tao et al.AAAI 2025 · 13 citations
  2. A Survey of AMR ApplicationsShira Wein, Juri OpitzEMNLP 2024 · 7 citations
  3. Error-driven Data-efficient Large Multimodal Model TuningBarry Menglong Yao, Qifan Wang, Lifu HuangACL 2025 · 1 citation

Builds on12

  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. Semi-supervised Relation Extraction via Incremental Meta Self-TrainingXuming Hu, Chenwei Zhang, Fukun Ma, Chenyao Liu et al.EMNLP Findings 2021 · 61 citations
  4. Query and Extract: Refining Event Extraction as Type-oriented Binary DecodingSijia Wang, Mo Yu, Shiyu Chang, Lichao Sun et al.ACL Findings 2022 · 60 citations
  5. Meta Self-training for Few-shot Neural Sequence LabelingYaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu et al.KDD 2021 · 56 citations

Related papers

  1. Resource-Enhanced Neural Model for Event Argument ExtractionJie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros et al.EMNLP Findings 2020 · 31 citations
  2. AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction ModelI-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan et al.ACL 2023 · 26 citations
  3. Boosting Event Extraction with Denoised Structure-to-Text AugmentationBo Wang, Heyan Huang, Xiaochi Wei, Ge Shi et al.ACL Findings 2023 · 6 citations
  4. An AMR-based Link Prediction Approach for Document-level Event Argument ExtractionYuqing Yang, Qipeng Guo, Xiangkun Hu, Yue Zhang et al.ACL 2023 · 26 citations
  5. CLEVE: Contrastive Pre-training for Event ExtractionZiqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin et al.ACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines