Confidence Modeling for Neural Semantic Parsing

Li Dong, Chris Quirk, Mirella Lapata


Abstract
In this work we focus on confidence modeling for neural semantic parsers which are built upon sequence-to-sequence models. We outline three major causes of uncertainty, and design various metrics to quantify these factors. These metrics are then used to estimate confidence scores that indicate whether model predictions are likely to be correct. Beyond confidence estimation, we identify which parts of the input contribute to uncertain predictions allowing users to interpret their model, and verify or refine its input. Experimental results show that our confidence model significantly outperforms a widely used method that relies on posterior probability, and improves the quality of interpretation compared to simply relying on attention scores.
Anthology ID:
P18-1069
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
743–753
Language:
URL:
https://aclanthology.org/P18-1069
DOI:
10.18653/v1/P18-1069
Bibkey:
Cite (ACL):
Li Dong, Chris Quirk, and Mirella Lapata. 2018. Confidence Modeling for Neural Semantic Parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 743–753, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Confidence Modeling for Neural Semantic Parsing (Dong et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/P18-1069.pdf
Presentation:
 P18-1069.Presentation.pdf
Code
 donglixp/confidence