End-to-end Parsing of Procedural Text into Flow Graphs

Dhaivat J. Bhatt, Seyed Ahmad Abdollahpouri Hosseini, Federico Fancellu, Afsaneh Fazly

Abstract
We focus on the problem of parsing procedural text into fine-grained flow graphs that encode actions and entities, as well as their interactions. Specifically, we focus on parsing cooking recipes, and address a few limitations of existing parsers. Unlike SOTA approaches to flow graph parsing that work in two separate stages identifying actions and entities (tagging) and encoding their interactions via connecting edges (graph generation). we propose an end-to-end multi-task framework that simultaneously performs tagging and graph generation. In addition, due to the end-to-end nature of our proposed model, we can unify the input representation, and moreover can use compact encoders, resulting in small models with significantly fewer parameters than SOTA models. Another key challenge in training flow graph parsers is the lack of sufficient annotated data, due to the costly nature of the fine-grained annotations. We address this problem by taking advantage of the abundant unlabelled recipes, and show that pre-training on automatically-generated noisy silver annotations (from unlabelled recipes) results in a large improvement in flow graph parsing.
Anthology ID:
2024.lrec-main.517
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5833–5842
Language:
URL:
https://aclanthology.org/2024.lrec-main.517
DOI:
Bibkey:
Cite (ACL):
Dhaivat J. Bhatt, Seyed Ahmad Abdollahpouri Hosseini, Federico Fancellu, and Afsaneh Fazly. 2024. End-to-end Parsing of Procedural Text into Flow Graphs. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5833–5842, Torino, Italia. ELRA and ICCL.
Cite (Informal):
End-to-end Parsing of Procedural Text into Flow Graphs (Bhatt et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.lrec-main.517.pdf
PDF Search