A Globally Normalized Neural Model for Semantic Parsing

2021/06/07 by Chenyang Huang, Huang, Chenyang, Wei Yang +8
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2106.03376

arxiv created 2021/06/07 · openalex publication_date 2021/06/07 · arxiv updated 2021/06/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Experiments show that our approach outperforms locally normalized models on small datasets, but it does not yield improvement on a large dataset.

Citations

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
• Optimizing Deeper Transformers on Small Datasets

Related

• Semantic Parsing: Syntactic assurance to target sentence using LSTM Encoder CFG-Decoder
• The Limitations of Limited Context for Constituency Parsing
• Three Generative, Lexicalised Models for Statistical Parsing
• Explaining Large Language Model-Based Neural Semantic Parsers (Student Abstract)
• A Probabilistic Generative Grammar for Semantic Parsing