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.
arXiv commentAccepted to EACL 2021
References in corpus (24)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Improving Text-to-SQL Evaluation Methodology
- Language to Logical Form with Neural Attention
- Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
- Grammar-based Neural Text-to-SQL Generation
- Coarse-to-Fine Decoding for Neural Semantic Parsing
- Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
- Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
- Data Recombination for Neural Semantic Parsing
- A Survey on Semantic Parsing
- Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
- TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
- One-Shot Learning for Text-to-SQL Generation
- Cross-domain Semantic Parsing via Paraphrasing
- Broad-Coverage Semantic Parsing as Transduction
- Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
- Zero-shot Text-to-SQL Learning with Auxiliary Task
- Zero-shot Transfer Learning for Semantic Parsing
- Merging Weak and Active Supervision for Semantic Parsing
- Domain Adaptation for Semantic Parsing