Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning
He, Zhitao, Cao, Pengfei, Jin, Zhuoran, Chen, Yubo, Liu, Kang, Zhang, Zhiqiang, Sun, Mengshu, Zhao, Jun
–arXiv.org Artificial Intelligence
Event Causality Identification (ECI) refers to the detection of causal relations between events in texts. However, most existing studies focus on sentence-level ECI with high-resource languages, leaving more challenging document-level ECI (DECI) with low-resource languages under-explored. In this paper, we propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning (GIMC) for zero-shot cross-lingual document-level ECI. Specifically, we introduce a heterogeneous graph interaction network to model the long-distance dependencies between events that are scattered over a document. Then, to improve cross-lingual transferability of causal knowledge learned from the source language, we propose a multi-granularity contrastive transfer learning module to align the causal representations across languages. Extensive experiments show our framework outperforms the previous state-of-the-art model by 9.4% and 8.2% of average F1 score on monolingual and multilingual scenarios respectively. Notably, in the multilingual scenario, our zero-shot framework even exceeds GPT-3.5 with few-shot learning by 24.3% in overall performance.
arXiv.org Artificial Intelligence
Mar-22-2024
- Country:
- Africa > Mali (0.05)
- North America
- Dominican Republic (0.04)
- United States
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- New York > New York County
- Canada > Ontario
- Toronto (0.04)
- Europe
- United Kingdom (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- Genre:
- Research Report (1.00)
- Instructional Material > Course Syllabus & Notes (0.48)
- Industry:
- Technology: