Few-Shot Semantic Parsing for New Predicates

2021/01/26 by Zhuang Li, Lizhen Qu, Li, Zhuang +5
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2101.10708

openalex publication_date 2021/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

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.

Citations

• Adam: A Method for Stochastic Optimization
• Long Short-Term Memory
• Sequence to Sequence Learning with Neural Networks
• Language to Logical Form with Neural Attention
• Data Recombination for Neural Semantic Parsing
• Prototypical Networks for Few-shot Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Coarse-to-Fine Decoding for Neural Semantic Parsing
• A Survey on Semantic Parsing
• Grammar-based Neural Text-to-SQL Generation
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• 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
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• Broad-Coverage Semantic Parsing as Transduction
• Merging Weak and Active Supervision for Semantic Parsing
• Domain Adaptation for Semantic Parsing

Related

• Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
• Learning Structured Natural Language Representations for Semantic Parsing
• Training Naturalized Semantic Parsers with Very Little Data
• Look-up and Adapt: A One-shot Semantic Parser
• On The Ingredients of an Effective Zero-shot Semantic Parser