Integrating Relational Knowledge With Text Sequences for Script Event Prediction
Zikang Wang; Linjing Li; Daniel Zeng
Source PublicationIEEE Transactions on Neural Networks and Learning Systems
2023
Pagesearly access
Abstract
Script event prediction aims to infer subsequent events given an incomplete script. It requires a deep understanding of events, and can provide support for a variety of tasks. Existing models rarely consider the relational knowledge between events, they regard scripts as sequences or graphs, which cannot capture the relational information between events and the  semantic information of script sequences jointly. To address this issue, we propose a new script form, relational event chain, that combines event chains and relational graphs. We also introduce a new model, relational-transformer, to learn embeddings based on this new script form. In particular, we fifirst extract the relationship between events from an event knowledge graph to formalize scripts as relational event chains, then use the relational-transformer to calculate the likelihood of different candidate events, where the model learns event embeddings that encode both semantic and relational knowledge by combining transformers and graph neural networks (GNNs). Experimental results on both one-step inference and multistep inference tasks show that our model can outperform existing baselines, indicating the validity of encoding relational knowledge into event embeddings. The inflfluence of using different model structures and different types of relational knowledge is analyzed as well.
Language英语
Sub direction classification知识表示与推理
planning direction of the national heavy laboratory语音语言处理
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/51442
Collection复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
AffiliationInstitute of Automation Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zikang Wang,Linjing Li,Daniel Zeng. Integrating Relational Knowledge With Text Sequences for Script Event Prediction[J]. IEEE Transactions on Neural Networks and Learning Systems,2023:early access.
APA Zikang Wang,Linjing Li,&Daniel Zeng.(2023).Integrating Relational Knowledge With Text Sequences for Script Event Prediction.IEEE Transactions on Neural Networks and Learning Systems,early access.
MLA Zikang Wang,et al."Integrating Relational Knowledge With Text Sequences for Script Event Prediction".IEEE Transactions on Neural Networks and Learning Systems (2023):early access.
Files in This Item: Download All
File Name/Size DocType Version Access License
2022_tnnls_event.pdf(3215KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zikang Wang]'s Articles
[Linjing Li]'s Articles
[Daniel Zeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zikang Wang]'s Articles
[Linjing Li]'s Articles
[Daniel Zeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zikang Wang]'s Articles
[Linjing Li]'s Articles
[Daniel Zeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2022_tnnls_event.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.