Few-Shot Semantic Parsing for New Predicates

Zhuang Li, Lizhen Qu, Shuo Huang, Gholamreza Haffari


Abstract
In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with k utterance-logical form pairs per new predicate. The state-of-the-art neural semantic parsers achieve less than 25% accuracy on benchmark datasets when k = 1. To tackle this problem, we proposed to i) apply a designated meta-learning method to train the model; ii) regularize attention scores with alignment statistics; iii) apply a smoothing technique in pretraining. As a result, our method consistently outperforms all the baselines in both one and two-shot settings.
Anthology ID:
2021.eacl-main.109
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1281–1291
Language:
URL:
https://aclanthology.org/2021.eacl-main.109
DOI:
10.18653/v1/2021.eacl-main.109
Bibkey:
Cite (ACL):
Zhuang Li, Lizhen Qu, Shuo Huang, and Gholamreza Haffari. 2021. Few-Shot Semantic Parsing for New Predicates. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1281–1291, Online. Association for Computational Linguistics.
Cite (Informal):
Few-Shot Semantic Parsing for New Predicates (Li et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.109.pdf
Code
 zhuang-li/few-shot-semantic-parsing