• Corpus ID: 173188416

Grammar-based Neural Text-to-SQL Generation

  title={Grammar-based Neural Text-to-SQL Generation},
  author={Kevin Lin and Ben Bogin and Mark Neumann and Jonathan Berant and Matt Gardner},
The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. [] Key Result We analyze these techniques on ATIS and Spider, two challenging text-to-SQL datasets, demonstrating that they yield 14--18\% relative reductions in error.

Figures and Tables from this paper

RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task

A novel recursive semantic parsing framework called RECPARSER is proposed to generate the nested SQL query layer-by-layer and achieves an overall accuracy that is comparable with state-of-the-art approaches.

A Pilot Study for Chinese SQL Semantic Parsing

A Spider dataset for Chinese is built, showing that word-based semantic parser is subject to segmentation errors and cross-lingual word embeddings are useful for text-to-SQL.

Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

This paper presents 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.

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

A new architecture, ShadowGNN, is proposed, which processes schemas at abstract and semantic levels, which outperforms state-of-the-art models on the challenging Text-to-SQL benchmark Spider and shows its powerful generalization ability.

PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

On the challenging Spider and CoSQL text-to-SQL translation tasks, it is shown that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.

Global Reasoning over Database Structures for Text-to-SQL Parsing

This work uses message-passing through a graph neural network to softly select a subset of database constants for the output query, conditioned on the question, and trains a model to rank queries based on the global alignment ofdatabase constants to question words.


This paper puts the light on another way to resolve natural language processing tasks, especially the Natural Language to SQL one using the method of sketch-based decoding which is based on a sketch with holes that the model incrementally tries to fill.

Photon: A Robust Cross-Domain Text-to-SQL System

PHOTON is presented, a robust, modular, cross-domain NLIDB that can flag natural language input to which a SQL mapping cannot be immediately determined and effectively improves the robustness of text-to-SQL system against untranslatable user input.

Re-examining the Role of Schema Linking in Text-to-SQL

This work provides a schema linking corpus based on the Spider text-to-SQL dataset, and builds a simple BERT-based baseline to perform a data-driven study on schema linking, finding when schema linking is done well, SLSQL demonstrates good performance on Spider despite its structural simplicity.

RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

A neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) is presented to solve complex Text-to-SQL tasks for cross-domain databases to improve generation performance further.



TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

TRANX is a transition-based neural semantic parser that maps natural language utterances into formal meaning representations (MRs) and is highly generalizable, extensible, and effective, registering strong results compared to existing neural semantic parsers.

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task

Experimental results show that SyntaxSQLNet can handle a significantly greater number of complex SQL examples than prior work, outperforming the previous state-of-the-art model by 9.5% in exact matching accuracy.

Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

A learning algorithm is described that takes as input a training set of sentences labeled with expressions in the lambda calculus and induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence.

Abstract Syntax Networks for Code Generation and Semantic Parsing

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling

Language to Logical Form with Neural Attention

This paper presents a general method based on an attention-enhanced encoder-decoder model that encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors.

Learning Dependency-Based Compositional Semantics

A new semantic formalism, dependency-based compositional semantics (DCS) is developed and a log-linear distribution over DCS logical forms is defined and it is shown that the system obtains comparable accuracies to even state-of-the-art systems that do require annotated logical forms.

Context-dependent Semantic Parsing for Time Expressions

This work uses a Combinatory Categorial Grammar to construct compositional meaning representations, while considering contextual cues, such as the document creation time and the tense of the governing verb, to compute the final time values.

Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

A new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables with a state-of-the-art accuracy and type constraints and entity linking are valuable components to incorporate in neural semantic parsers.

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

A Neural Symbolic Machine is introduced, which contains a neural “programmer” that maps language utterances to programs and utilizes a key-variable memory to handle compositionality, and a symbolic “computer”, i.e., a Lisp interpreter that performs program execution, and helps find good programs by pruning the search space.

Learning a Neural Semantic Parser from User Feedback

We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal