Few-Shot Semantic Parsing for New Predicates
arXiv:2101.10708
Abstract
In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with 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 pre-training. As a result, our method consistently outperforms all the baselines in both one and two-shot settings.
Accepted to EACL 2021
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Grammar-based Neural Text-to-SQL Generation
- Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
- One-Shot Learning for Text-to-SQL Generation
- Merging Weak and Active Supervision for Semantic Parsing
- Domain Adaptation for Semantic Parsing