Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback

Carolin Lawrence, Stefan Riezler


Abstract
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies in a proper reweighting of the estimator so as to avoid known degeneracies in counterfactual learning, while still being applicable to stochastic gradient optimization. To conduct experiments with human users, we devise an easy-to-use interface to collect human feedback on semantic parses. Our work is the first to show that semantic parsers can be improved significantly by counterfactual learning from logged human feedback data.
Anthology ID:
P18-1169
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:
1820–1830
Language:
URL:
https://aclanthology.org/P18-1169
DOI:
10.18653/v1/P18-1169
Bibkey:
Cite (ACL):
Carolin Lawrence and Stefan Riezler. 2018. Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1820–1830, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (Lawrence & Riezler, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1169.pdf
Note:
 P18-1169.Notes.pdf
Presentation:
 P18-1169.Presentation.pdf
Video:
 https://aclanthology.org/P18-1169.mp4
Code
 carolinlawrence/nematus