Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time. In Spider, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query. In this paper, we present an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time. Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.
Code (1)
Tasks
DecoderGraph Neural NetworkSQL ParsingText to SQLText-To-SQLSimilar Papers 제목 키워드 기반
A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and t…
Graph Neural NetworkSemantic ParsingSQL ParsingText to SQL+1CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers
Context-dependent text-to-SQL is the task of translating multi-turn questions into database-related SQL queries. Existing methods typically focus on making full use of history context or previously predicted SQL for curr…
SQL ParsingText to SQLText-To-SQLFast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing
This paper proposes to cast end-to-end span-based SRL as a word-based graph parsing task. The major challenge is how to represent spans at the word level. Borrowing ideas from research on Chinese word segmentation and na…
Chinese Word Segmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1Schema-Free Dependency Parsing via Sequence Generation
Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods suffer the drawbacks of lacking universality or highly relying on the auxiliary decoder. …
DecoderDependency ParsingLanguage ModellingSchema-Free Dependency Parsing via Sequence Generation
Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods suffer the drawbacks of lacking universality or highly relying on the auxiliary decoder. …
DecoderDependency ParsingLanguage Modelling