ACL Findings2021
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Xinyu Zuo, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Weihua Peng, Yuguang Chen
Abstract
Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficient support for models to capture useful indicators from causal statements, especially for handing those new, unseen cases. To alleviate this problem, we propose a novel approach, shortly named CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. Then, we adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model. Experimental results show that our method significantly outperforms previous methods on EventSto-ryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively).
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.
10 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- CURL: Contrastive Unsupervised Representations for Reinforcement Learning cites A Simple Framework for Contrastive Learning of Visual Representations
- Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning cites A Simple Framework for Contrastive Learning of Visual Representations
- Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models cites Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction
- Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models cites Semantic Structure Enhanced Event Causality Identification
- Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models cites CHEER: Centrality-aware High-order Event Reasoning Network for Document-level Event Causality Identification
- Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models cites Identify Event Causality with Knowledge and Analogy
Cited by top-tier papers10
- CHEER: Centrality-aware High-order Event Reasoning Network for Document-level Event Causality IdentificationMeiqi Chen, Yixin Cao, Yan Zhang, Zhiwei LiuACL 2023 · 18 citations
- Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation ExtractionChangsen Yuan, Heyan Huang, Yixin Cao, Yonggang WenACL 2023 · 14 citations
- Semantic Structure Enhanced Event Causality IdentificationZhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai et al.ACL 2023 · 14 citations
- Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion ModelsHieu Man, Franck Dernoncourt, Thien Huu NguyenAAAI 2024 · 12 citations
- Identify Event Causality with Knowledge and AnalogySifan Wu, Ruihui Zhao, Yefeng Zheng, Jian Pei et al.AAAI 2023 · 12 citations
Builds on6
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
- Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningJean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec et al.NeurIPS 2020 · 9,171 citations
- Contrastive Representation DistillationYonglong Tian, Dilip Krishnan, Phillip IsolaICLR 2020 · 1,305 citations
- CURL: Contrastive Unsupervised Representations for Reinforcement LearningMichael Laskin, Aravind Srinivas, Pieter AbbeelICML 2020 · 1,261 citations
- GLUCOSE: GeneraLized and COntextualized Story ExplanationsNasrin Mostafazadeh, Aditya Kalyanpur, Lori Moon, David W. Buchanan et al.EMNLP 2020 · 7 citations
Related papers
- In-context Contrastive Learning for Event Causality IdentificationChao Liang, Wei Xiang, Bang WangEMNLP 2024 · 7 citations
- LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality IdentificationXinyu Zuo, Pengfei Cao, Yubo Chen, Kang Liu et al.ACL 2021
- Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction GraphRuili Pu, Yang Li, Suge Wang, Deyu Li et al.ACL Findings 2023 · 14 citations
- Dynamic Energy-Based Contrastive Learning with Multi-Stage Knowledge Verification for Event Causality IdentificationYa Su, Hu Zhang, Yue Fan, Guangjun Zhang et al.EMNLP 2025
- Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry NetworkHaoran Li, Qiang Gao, Hongmei Wu, Li HuangEMNLP 2024 · 5 citations
