Look-up and Adapt: A One-shot Semantic Parser

Zhichu Lu, Forough Arabshahi, Igor Labutov, Tom Mitchell

[How to correct problems with metadata yourself]

Abstract
Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited “supported” domain of discourse and fail drastically when faced with an out-of-domain utterance, mainly due to the limitations of their semantic parser. In this paper, we propose a semantic parser that generalizes to out-of-domain examples by learning a general strategy for parsing an unseen utterance through adapting the logical forms of seen utterances, instead of learning to generate a logical form from scratch. Our parser maintains a memory consisting of a representative subset of the seen utterances paired with their logical forms. Given an unseen utterance, our parser works by looking up a similar utterance from the memory and adapting its logical form until it fits the unseen utterance. Moreover, we present a data generation strategy for constructing utterance-logical form pairs from different domains. Our results show an improvement of up to 68.8% on one-shot parsing under two different evaluation settings compared to the baselines.
Anthology ID:
D19-1104
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1129–1139
Language:
URL:
https://aclanthology.org/D19-1104
DOI:
10.18653/v1/D19-1104
Bibkey:
Cite (ACL):
Zhichu Lu, Forough Arabshahi, Igor Labutov, and Tom Mitchell. 2019. Look-up and Adapt: A One-shot Semantic Parser. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1129–1139, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Look-up and Adapt: A One-shot Semantic Parser (Lu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D19-1104.pdf
Attachment:
 D19-1104.Attachment.zip
Code
 zhichul/lookup-and-adapt-parser-data
PDF Search Code Attachment