Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog

Panupong Pasupat, Sonal Gupta, Karishma Mandyam, Rushin Shah, Mike Lewis, Luke Zettlemoyer


Abstract
We propose a semantic parser for parsing compositional utterances into Task Oriented Parse (TOP), a tree representation that has intents and slots as labels of nesting tree nodes. Our parser is span-based: it scores labels of the tree nodes covering each token span independently, but then decodes a valid tree globally. In contrast to previous sequence decoding approaches and other span-based parsers, we (1) improve the training speed by removing the need to run the decoder at training time; and (2) introduce edge scores, which model relations between parent and child labels, to mitigate the independence assumption between node labels and improve accuracy. Our best parser outperforms previous methods on the TOP dataset of mixed-domain task-oriented utterances in both accuracy and training speed.
Anthology ID:
D19-1163
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
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1520–1526
Language:
URL:
https://aclanthology.org/D19-1163
DOI:
10.18653/v1/D19-1163
Bibkey:
Cite (ACL):
Panupong Pasupat, Sonal Gupta, Karishma Mandyam, Rushin Shah, Mike Lewis, and Luke Zettlemoyer. 2019. Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog. 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 1520–1526, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog (Pasupat et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1163.pdf
Attachment:
 D19-1163.Attachment.zip