Few-Shot Semantic Parsing for New Predicates
This work addresses the challenge of adapting semantic parsers to new predicates with limited data, which is incremental as it builds on existing methods to improve performance.
The paper tackles the problem of low accuracy in few-shot semantic parsing for new predicates, where existing parsers achieve less than 25% accuracy with one example, and proposes a method that outperforms baselines in one- and two-shot settings.
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.