Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17480 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913519305228288 |
|---|---|
| author | Zhan, Chuanhong Xiang, Wei Liang, Chao Wang, Bang |
| author_facet | Zhan, Chuanhong Xiang, Wei Liang, Chao Wang, Bang |
| contents | Existing script event prediction task forcasts the subsequent event based on an event script chain. However, the evolution of historical events are more complicated in real world scenarios and the limited information provided by the event script chain also make it difficult to accurately predict subsequent events. This paper introduces a Causality Graph Event Prediction(CGEP) task that forecasting consequential event based on an Event Causality Graph (ECG). We propose a Semantic Enhanced Distance-sensitive Graph Prompt Learning (SeDGPL) Model for the CGEP task. In SeDGPL, (1) we design a Distance-sensitive Graph Linearization (DsGL) module to reformulate the ECG into a graph prompt template as the input of a PLM; (2) propose an Event-Enriched Causality Encoding (EeCE) module to integrate both event contextual semantic and graph schema information; (3) propose a Semantic Contrast Event Prediction (ScEP) module to enhance the event representation among numerous candidate events and predict consequential event following prompt learning paradigm. %We construct two CGEP datasets based on existing MAVEN-ERE and ESC corpus for experiments. Experiment results validate our argument our proposed SeDGPL model outperforms the advanced competitors for the CGEP task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What Would Happen Next? Predicting Consequences from An Event Causality Graph Zhan, Chuanhong Xiang, Wei Liang, Chao Wang, Bang Artificial Intelligence Existing script event prediction task forcasts the subsequent event based on an event script chain. However, the evolution of historical events are more complicated in real world scenarios and the limited information provided by the event script chain also make it difficult to accurately predict subsequent events. This paper introduces a Causality Graph Event Prediction(CGEP) task that forecasting consequential event based on an Event Causality Graph (ECG). We propose a Semantic Enhanced Distance-sensitive Graph Prompt Learning (SeDGPL) Model for the CGEP task. In SeDGPL, (1) we design a Distance-sensitive Graph Linearization (DsGL) module to reformulate the ECG into a graph prompt template as the input of a PLM; (2) propose an Event-Enriched Causality Encoding (EeCE) module to integrate both event contextual semantic and graph schema information; (3) propose a Semantic Contrast Event Prediction (ScEP) module to enhance the event representation among numerous candidate events and predict consequential event following prompt learning paradigm. %We construct two CGEP datasets based on existing MAVEN-ERE and ESC corpus for experiments. Experiment results validate our argument our proposed SeDGPL model outperforms the advanced competitors for the CGEP task. |
| title | What Would Happen Next? Predicting Consequences from An Event Causality Graph |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2409.17480 |