Reasoning over Entity-Action-Location Graph for Procedural Text Understanding

Hao Huang, Xiubo Geng, Jian Pei, Guodong Long, Daxin Jiang


Abstract
Procedural text understanding aims at tracking the states (e.g., create, move, destroy) and locations of the entities mentioned in a given paragraph. To effectively track the states and locations, it is essential to capture the rich semantic relations between entities, actions, and locations in the paragraph. Although recent works have achieved substantial progress, most of them focus on leveraging the inherent constraints or incorporating external knowledge for state prediction. The rich semantic relations in the given paragraph are largely overlooked. In this paper, we propose a novel approach (REAL) to procedural text understanding, where we build a general framework to systematically model the entity-entity, entity-action, and entity-location relations using a graph neural network. We further develop algorithms for graph construction, representation learning, and state and location tracking. We evaluate the proposed approach on two benchmark datasets, ProPara, and Recipes. The experimental results show that our method outperforms strong baselines by a large margin, i.e., 5.0% on ProPara and 3.2% on Recipes, illustrating the utility of semantic relations and the effectiveness of the graph-based reasoning model.
Anthology ID:
2021.acl-long.396
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5100–5109
Language:
URL:
https://aclanthology.org/2021.acl-long.396
DOI:
10.18653/v1/2021.acl-long.396
Bibkey:
Cite (ACL):
Hao Huang, Xiubo Geng, Jian Pei, Guodong Long, and Daxin Jiang. 2021. Reasoning over Entity-Action-Location Graph for Procedural Text Understanding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5100–5109, Online. Association for Computational Linguistics.
Cite (Informal):
Reasoning over Entity-Action-Location Graph for Procedural Text Understanding (Huang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.396.pdf
Video:
 https://aclanthology.org/2021.acl-long.396.mp4
Data
ConceptNetProPara