Few-Shot Semantic Parsing for New Predicates
Zhuang Li, Lizhen Qu, shuo huang, Gholamreza Haffari
Semantics: Sentence-level Semantics, Textual Inference and Other areas Long paper Paper
You can open the pre-recorded video in separate windows.
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.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.