Tracking Discrete and Continuous Entity State for Process Understanding

Aditya Gupta, Greg Durrett


Abstract
Procedural text, which describes entities and their interactions as they undergo some process, depicts entities in a uniquely nuanced way. First, each entity may have some observable discrete attributes, such as its state or location; modeling these involves imposing global structure and enforcing consistency. Second, an entity may have properties which are not made explicit but can be effectively induced and tracked by neural networks. In this paper, we propose a structured neural architecture that reflects this dual nature of entity evolution. The model tracks each entity recurrently, updating its hidden continuous representation at each step to contain relevant state information. The global discrete state structure is explicitly modelled with a neural CRF over the changing hidden representation of the entity. This CRF can explicitly capture constraints on entity states over time, enforcing that, for example, an entity cannot move to a location after it is destroyed. We evaluate the performance of our proposed model on QA tasks over process paragraphs in the ProPara dataset and find that our model achieves state-of-the-art results.
Anthology ID:
W19-1502
Volume:
Proceedings of the Third Workshop on Structured Prediction for NLP
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Andre Martins, Andreas Vlachos, Zornitsa Kozareva, Sujith Ravi, Gerasimos Lampouras, Vlad Niculae, Julia Kreutzer
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7–12
Language:
URL:
https://aclanthology.org/W19-1502
DOI:
10.18653/v1/W19-1502
Bibkey:
Cite (ACL):
Aditya Gupta and Greg Durrett. 2019. Tracking Discrete and Continuous Entity State for Process Understanding. In Proceedings of the Third Workshop on Structured Prediction for NLP, pages 7–12, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Tracking Discrete and Continuous Entity State for Process Understanding (Gupta & Durrett, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-1502.pdf
Data
ProPara