Coalescing Global and Local Information for Procedural Text Understanding

Kaixin Ma, Filip Ilievski, Jonathan Francis, Eric Nyberg, Alessandro Oltramari


Abstract
Procedural text understanding is a challenging language reasoning task that requires models to track entity states across the development of a narrative. We identify three core aspects required for modeling this task, namely the local and global view of the inputs, as well as the global view of outputs. Prior methods have considered a subset of these aspects, which leads to either low precision or low recall. In this paper, we propose a new model Coalescing Global and Local Information (CGLI), which builds entity- and timestep-aware input representations (local input) considering the whole context (global input), and we jointly model the entity states with a structured prediction objective (global output). Thus, CGLI simultaneously optimizes for both precision and recall. Moreover, we extend CGLI with additional output layers and integrate it into a story reasoning framework. Extensive experiments on a popular procedural text understanding dataset show that our model achieves state-of-the-art results, while experiments on a story reasoning benchmark show the positive impact of our model on downstream reasoning.
Anthology ID:
2022.coling-1.132
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1534–1545
Language:
URL:
https://aclanthology.org/2022.coling-1.132
DOI:
Bibkey:
Cite (ACL):
Kaixin Ma, Filip Ilievski, Jonathan Francis, Eric Nyberg, and Alessandro Oltramari. 2022. Coalescing Global and Local Information for Procedural Text Understanding. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1534–1545, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Coalescing Global and Local Information for Procedural Text Understanding (Ma et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.132.pdf
Code
 mayer123/cgli
Data
ProParaSQuADTRIP