Context Dependent Semantic Parsing over Temporally Structured Data

Charles Chen, Razvan Bunescu


Abstract
We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a database and the user interacts with the system to obtain a better understanding of the entity’s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We design an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When trained to predict tokens using supervised learning, the proposed architecture substantially outperforms standard sequence generation baselines. Training the architecture using policy gradient leads to further improvements in performance, reaching a sequence-level accuracy of 88.7% on artificial data and 74.8% on real data.
Anthology ID:
N19-1360
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3576–3585
Language:
URL:
https://aclanthology.org/N19-1360
DOI:
10.18653/v1/N19-1360
Bibkey:
Cite (ACL):
Charles Chen and Razvan Bunescu. 2019. Context Dependent Semantic Parsing over Temporally Structured Data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3576–3585, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Context Dependent Semantic Parsing over Temporally Structured Data (Chen & Bunescu, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1360.pdf
Supplementary:
 N19-1360.Supplementary.pdf