Papers by Chuanhong Zhan

2 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations