Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

Jayant Krishnamurthy, Pradeep Dasigi, Matt Gardner


Abstract
We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed logical forms; and (2) an entity embedding and linking module that identifies entity mentions while generalizing across tables. We also introduce a novel method for training our neural model with question-answer supervision. On the WikiTableQuestions data set, our parser achieves a state-of-the-art accuracy of 43.3% for a single model and 45.9% for a 5-model ensemble, improving on the best prior score of 38.7% set by a 15-model ensemble. These results suggest that type constraints and entity linking are valuable components to incorporate in neural semantic parsers.
Anthology ID:
D17-1160
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1516–1526
Language:
URL:
https://aclanthology.org/D17-1160
DOI:
10.18653/v1/D17-1160
Bibkey:
Cite (ACL):
Jayant Krishnamurthy, Pradeep Dasigi, and Matt Gardner. 2017. Neural Semantic Parsing with Type Constraints for Semi-Structured Tables. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1516–1526, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables (Krishnamurthy et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1160.pdf
Video:
 https://vimeo.com/238234920
Code
 allenai/pnp