The Role of Semantic Parsing in Understanding Procedural Text

Hossein Rajaby Faghihi, Parisa Kordjamshidi, Choh Man Teng, James Allen


Abstract
In this paper, we investigate whether symbolic semantic representations, extracted from deep semantic parsers, can help reasoning over the states of involved entities in a procedural text. We consider a deep semantic parser (TRIPS) and semantic role labeling as two sources of semantic parsing knowledge. First, we propose PROPOLIS, a symbolic parsing-based procedural reasoning framework. Second, we integrate semantic parsing information into state-of-the-art neural models to conduct procedural reasoning. Our experiments indicate that explicitly incorporating such semantic knowledge improves procedural understanding. This paper presents new metrics for evaluating procedural reasoning tasks that clarify the challenges and identify differences among neural, symbolic, and integrated models.
Anthology ID:
2023.findings-eacl.137
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1837–1849
Language:
URL:
https://aclanthology.org/2023.findings-eacl.137
DOI:
10.18653/v1/2023.findings-eacl.137
Bibkey:
Cite (ACL):
Hossein Rajaby Faghihi, Parisa Kordjamshidi, Choh Man Teng, and James Allen. 2023. The Role of Semantic Parsing in Understanding Procedural Text. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1837–1849, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
The Role of Semantic Parsing in Understanding Procedural Text (Rajaby Faghihi et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.137.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.137.mp4