A Hybrid Semantic Parsing Approach for Tabular Data Analysis
arXiv:1910.10363
Abstract
This paper presents a novel approach to translating natural language questions to SQL queries for given tables, which meets three requirements as a real-world data analysis application: cross-domain, multilingualism and enabling quick-start. Our proposed approach consists of: (1) a novel data abstraction step before the parser to make parsing table-agnosticism; (2) a set of semantic rules for parsing abstracted data-analysis questions to intermediate logic forms as tree derivations to reduce the search space; (3) a neural-based model as a local scoring function on a span-based semantic parser for structured optimization and efficient inference. Experiments show that our approach outperforms state-of-the-art algorithms on a large open benchmark dataset WikiSQL. We also achieve promising results on a small dataset for more complex queries in both English and Chinese, which demonstrates our language expansion and quick-start ability.
arXiv comment10 pages, 5 figures
References in corpus (6)
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- The Natural Language Decathlon: Multitask Learning as Question Answering
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Lambda Dependency-Based Compositional Semantics
- Learning to Compute Word Embeddings On the Fly
- Semantic Parsing with Syntax- and Table-Aware SQL Generation