Few-Shot Semantic Parsing for New Predicates
By Zhuang Li, Lizhen Qu, Shuo Huang, Gholamreza Haffari. 2021
10 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Gholamreza Haffari
- Kelvin Guu
- Panupong Pasupat
- Lizhen Qu
- Zhuang Li
- Yuan Zhang
- Percy Liang
- Jonathan Berant
In Computer Vision and Pattern Recognition
- Panupong Pasupat
- Lizhen Qu
- Yuan Zhang
- Kelvin Guu
- Gholamreza Haffari
- Zhuang Li
- Jonathan Berant
- Percy Liang
Citations in the corpus
- Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, background): “There are also work (Guo et al., 2019; Wang et al., 2020a; Li et al., 2021) exploring semantic parsing with unseen database schemas or actions.”
- Controllable Semantic Parsing via Retrieval Augmentation (2021, methodology): “Data preprocessing We used the entire English portion of the MTOP dataset (Li et al., 2021a .”