Learning to Map Context-Dependent Sentences to Executable Formal Queries

Alane Suhr, Srinivasan Iyer, Yoav Artzi


Abstract
We propose a context-dependent model to map utterances within an interaction to executable formal queries. To incorporate interaction history, the model maintains an interaction-level encoder that updates after each turn, and can copy sub-sequences of previously predicted queries during generation. Our approach combines implicit and explicit modeling of references between utterances. We evaluate our model on the ATIS flight planning interactions, and demonstrate the benefits of modeling context and explicit references.
Anthology ID:
N18-1203
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2238–2249
Language:
URL:
https://aclanthology.org/N18-1203
DOI:
10.18653/v1/N18-1203
Bibkey:
Cite (ACL):
Alane Suhr, Srinivasan Iyer, and Yoav Artzi. 2018. Learning to Map Context-Dependent Sentences to Executable Formal Queries. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2238–2249, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Learning to Map Context-Dependent Sentences to Executable Formal Queries (Suhr et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-1203.pdf
Note:
 N18-1203.Notes.pdf
Video:
 https://aclanthology.org/N18-1203.mp4
Code
 clic-lab/atis
Data
ATIS