Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline

Haopeng Ren, Yushi Zeng, Yi Cai, Bihan Zhou, Zetao Lian


Abstract
Current structured and semi-structured knowledge bases mainly focus on representing descriptive knowledge but ignore another commonsense knowledge (Procedural Knowledge). To structure the procedural knowledge, existing methods are proposed to automatically generate flow graphs from procedural documents. They focus on extracting sequential dependency between sentences but neglect another two important dependencies (i.e., inclusion dependency and constraint dependency) in procedural documents. In our paper, we explore a problem of automatically generating procedural graph with multiple dependency relations to extend the flow graph constructed by existing methods and propose a procedural graph construction method with syntactic information and discourse structures. A new dataset (WHPG) is built and extensive experiments are conducted to evaluate the effectiveness of our proposed model.
Anthology ID:
2023.findings-acl.536
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8474–8486
Language:
URL:
https://aclanthology.org/2023.findings-acl.536
DOI:
10.18653/v1/2023.findings-acl.536
Bibkey:
Cite (ACL):
Haopeng Ren, Yushi Zeng, Yi Cai, Bihan Zhou, and Zetao Lian. 2023. Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8474–8486, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline (Ren et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.536.pdf