Graph-Based Decoding for Task Oriented Semantic Parsing

Jeremy Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He, Peter Shaw


Abstract
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.
Anthology ID:
2021.findings-emnlp.341
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4057–4065
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.341
DOI:
10.18653/v1/2021.findings-emnlp.341
Bibkey:
Cite (ACL):
Jeremy Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He, and Peter Shaw. 2021. Graph-Based Decoding for Task Oriented Semantic Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4057–4065, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Graph-Based Decoding for Task Oriented Semantic Parsing (Cole et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.341.pdf