Be Consistent! Improving Procedural Text Comprehension using Label Consistency

Xinya Du, Bhavana Dalvi, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie


Abstract
Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is challenging as the world is changing throughout the text, and despite recent advances, current systems still struggle with this task. Our approach is to leverage the fact that, for many procedural texts, multiple independent descriptions are readily available, and that predictions from them should be consistent (label consistency). We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction performance (F1) over prior state-of-the-art systems.
Anthology ID:
N19-1244
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2347–2356
Language:
URL:
https://aclanthology.org/N19-1244
DOI:
10.18653/v1/N19-1244
Bibkey:
Cite (ACL):
Xinya Du, Bhavana Dalvi, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, and Claire Cardie. 2019. Be Consistent! Improving Procedural Text Comprehension using Label Consistency. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2347–2356, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Be Consistent! Improving Procedural Text Comprehension using Label Consistency (Du et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/N19-1244.pdf
Code
 allenai/propara
Data
ProPara