AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing

Xiang Zhang, Shizhu He, Kang Liu, Jun Zhao


Abstract
Neural semantic parsers utilize the encoder-decoder framework to learn an end-to-end model for semantic parsing that transduces a natural language sentence to the formal semantic representation. To keep the model aware of the underlying grammar in target sequences, many constrained decoders were devised in a multi-stage paradigm, which decode to the sketches or abstract syntax trees first, and then decode to target semantic tokens. We instead to propose an adaptive decoding method to avoid such intermediate representations. The decoder is guided by model uncertainty and automatically uses deeper computations when necessary. Thus it can predict tokens adaptively. Our model outperforms the state-of-the-art neural models and does not need any expertise like predefined grammar or sketches in the meantime.
Anthology ID:
P19-1418
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4265–4270
Language:
URL:
https://aclanthology.org/P19-1418
DOI:
10.18653/v1/P19-1418
Bibkey:
Cite (ACL):
Xiang Zhang, Shizhu He, Kang Liu, and Jun Zhao. 2019. AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4265–4270, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing (Zhang et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1418.pdf
Software:
 P19-1418.Software.zip
Video:
 https://aclanthology.org/P19-1418.mp4