Papers by Chuanhong Zhan
What Would Happen Next? Predicting Consequences from An Event Causality Graph (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing script event prediction task forcasts the subsequent event based on an event script chain, but the evolution of historical events is more complicated in real world scenarios. |
| Approach: | They propose a Causality Graph Event Prediction task that forecasts consequential event based on an Event Causity Graph (ECG). |
| Outcome: | The proposed model outperforms the advanced competitors for the CGEP task. |
Evaluating Instructively Generated Statement by Large Language Models for Directional Event Causality Identification (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on identifying existence of causality between two event mentions, but the direction of causalities is crucial for understanding the causal relation. |
| Approach: | They propose to instruct a GLM to generate causality statements and identify directional event causality by evaluating the generated statements. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods even with fewer training data. |