Dependency-based Hybrid Trees for Semantic Parsing

Zhanming Jie, Wei Lu


Abstract
We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is interpreted as the latent dependency between the natural language words in our joint representation. Such dependency information can capture the interactions between the semantics and natural language words. We integrate a neural component into our model and propose an efficient dynamic-programming algorithm to perform tractable inference. Through extensive experiments on the standard multilingual GeoQuery dataset with eight languages, we demonstrate that our proposed approach is able to achieve state-of-the-art performance across several languages. Analysis also justifies the effectiveness of using our new dependency-based representation.
Anthology ID:
D18-1265
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2431–2441
Language:
URL:
https://aclanthology.org/D18-1265
DOI:
10.18653/v1/D18-1265
Bibkey:
Cite (ACL):
Zhanming Jie and Wei Lu. 2018. Dependency-based Hybrid Trees for Semantic Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2431–2441, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Dependency-based Hybrid Trees for Semantic Parsing (Jie & Lu, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1265.pdf
Attachment:
 D18-1265.Attachment.zip
Video:
 https://aclanthology.org/D18-1265.mp4