Coarse-to-Fine Decoding for Neural Semantic Parsing

Abstract

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an input utterance, we first generate a rough sketch of its meaning, where low-level information (such as variable names and arguments) is glossed over. Then, we fill in missing details by taking into account the natural language input and the sketch itself. Experimental results on four datasets characteristic of different domains and meaning representations show that our approach consistently improves performance, achieving competitive results despite the use of relatively simple decoders.

arXiv commentAccepted by ACL-18

References in corpus (3)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

Cited by in corpus (18)

• The Natural Language Decathlon: Multitask Learning as Question Answering
• TreeGen: A Tree-Based Transformer Architecture for Code Generation
• Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parsers
• Toward Code Generation: A Survey and Lessons from Semantic Parsing
• Table2answer: Read the database and answer without SQL
• Query Understanding for Natural Language Enterprise Search
• Representing Partial Programs with Blended Abstract Semantics
• Merging Weak and Active Supervision for Semantic Parsing
• Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
• Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
• Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering
• Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
• Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning
• Few-Shot Semantic Parsing for New Predicates
• Context Dependent Semantic Parsing: A Survey
• On Robustness of Neural Semantic Parsers
• FANDA: A Novel Approach to Perform Follow-up Query Analysis
• A survey of cross-lingual features for zero-shot cross-lingual semantic parsing