Learning from Executions for Semantic Parsing

Bailin Wang, Mirella Lapata, Ivan Titov


Abstract
Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged as a major bottleneck for the deployment of contemporary neural models to real-life applications. In this work, we focus on the task of semi-supervised learning where a limited amount of annotated data is available together with many unlabeled NL utterances. Based on the observation that programs which correspond to NL utterances should always be executable, we propose to encourage a parser to generate executable programs for unlabeled utterances. Due to the large search space of executable programs, conventional methods that use beam-search for approximation, such as self-training and top-k marginal likelihood training, do not perform as well. Instead, we propose a set of new training objectives that are derived by approaching the problem of learning from executions from the posterior regularization perspective. Our new objectives outperform conventional methods on Overnight and GeoQuery, bridging the gap between semi-supervised and supervised learning.
Anthology ID:
2021.naacl-main.219
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2747–2759
Language:
URL:
https://aclanthology.org/2021.naacl-main.219
DOI:
10.18653/v1/2021.naacl-main.219
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.219.pdf
Code
 berlino/tensor2struct-public