Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion

TL;DR

This paper introduces UniCE, a unified framework for Event Causality Extraction that effectively models subtask interactions and fuses knowledge from language models and knowledge graphs, achieving state-of-the-art results.

Contribution

The paper proposes a novel unified ECE framework with subtask interaction and knowledge fusion mechanisms, addressing complex causality, subtask dependence, and multimodal knowledge integration.

Findings

Achieves state-of-the-art performance on three benchmark datasets.

Outperforms ChatGPT by at least 30% F1-score.

Enhances ChatGPT's ECE performance via in-context learning.

Abstract

Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT's recent success, fine-tuning small models remains the best approach for the ECE task. However, existing fine-tuning based ECE methods cannot address all three key challenges in ECE simultaneously: 1) Complex Causality Extraction, where multiple causal-effect pairs occur within a single sentence; 2) Subtask~ Interaction, which involves modeling the mutual dependence between the two subtasks of ECE, i.e., extracting events and identifying the causal relationship between extracted events; and 3) Knowledge Fusion, which requires effectively fusing the knowledge in two modalities, i.e., the expressive pretrained language models and the structured knowledge graphs. In this paper, we propose a unified ECE framework (UniCE to address all three issues in ECE simultaneously. Specifically, we design a subtask interaction mechanism to enable mutual interaction between the two ECE subtasks. Besides, we design a knowledge fusion mechanism to fuse knowledge in the two modalities. Furthermore, we employ separate decoders for each subtask to facilitate complex causality extraction. Experiments on three benchmark datasets demonstrate that our method achieves state-of-the-art performance and outperforms ChatGPT with a margin of at least 30% F1-score. More importantly, our model can also be used to effectively improve the ECE performance of ChatGPT via in-context learning.