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

@article{Bogin2019GlobalRO,
  title={Global Reasoning over Database Structures for Text-to-SQL Parsing},
  author={Ben Bogin and Matt Gardner and Jonathan Berant},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.11214}
}
State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. [...] Key Method We use message-passing through a graph neural network to softly select a subset of database constants for the output query, conditioned on the question. Moreover, we train a model to rank queries based on the global alignment of database constants to question words. We apply our techniques to the current state-of-the-art model for Spider, a zero-shot semantic parsing dataset with complex databases…Expand
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
TLDR
GraPPa is an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data and significantly outperforms RoBERTa-large as the feature representation layers and establishes new state-of-the-art results on all of them. Expand
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
TLDR
This work presents BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing that effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks. Expand
Service-oriented Text-to-SQL Parsing
TLDR
A service-oriented Text-to-SQL parser that translates natural language utterance to structural and executable SQL query and a algorithmic framework named Semantic-Enriched SQL generator (SE-SQL) that enables flexibly access database than rigid API in the application while keeping the performance quality for the most commonly used cases. Expand
Photon: A Robust Cross-Domain Text-to-SQL System
TLDR
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. Expand
Exploring Unexplored Generalization Challenges for Cross-Database Semantic Parsing
TLDR
This work re-purpose eight semantic parsing datasets that have been well-studied in the setting where in-domain training data is available, and instead use them as additional evaluation data for XSP systems instead, to uncovers several generalization challenges for cross-database semantic parsing. Expand
Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
TLDR
Two kinds of interaction states are defined based on schema items and SQL keywords separately, and a relational graph neural network and a non-linear layer are designed to update the representations of these two states respectively. Expand
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
TLDR
A model pre-training framework, GenerationAugmented Pre-training (GAP), that jointly learns representations of natural language utterances and table schemas by leveraging generation models to generate pre-train data to mitigate issues of existing general-purpose language models. Expand
RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task
TLDR
This paper proposes a novel recursive semantic parsing framework called RECPARSER to generate the nested SQL query layer-by-layer, and decomposes the complicated nestedSQL query generation problem into several progressive non-nested SQL query generation problems. Expand
RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases
TLDR
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. Expand
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
TLDR
TaBERT is a pretrained LM that jointly learns representations for NL sentences and (semi-)structured tables that achieves new best results on the challenging weakly-supervised semantic parsing benchmark WikiTableQuestions, while performing competitively on the text-to-SQL dataset Spider. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
TLDR
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. Expand
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task
TLDR
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. Expand
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
TLDR
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. Expand
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
TLDR
This work defines a new complex and cross-domain semantic parsing and text-to-SQL task so that different complicated SQL queries and databases appear in train and test sets and experiments with various state-of-the-art models show that Spider presents a strong challenge for future research. Expand
Sequence-based Structured Prediction for Semantic Parsing
TLDR
An approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query and shows how grammatical constraints on the derivation sequence can easily be integrated inside the RNN-based sequential predictor. Expand
Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
TLDR
This paper introduces a zero-shot approach to semantic parsing that can parse utterances in unseen domains while only being trained on examples in other source domains. Expand
Discriminative Reranking for Natural Language Parsing
TLDR
The boosting approach to ranking problems described in Freund et al. (1998) is applied to parsing the Wall Street Journal treebank, and it is argued that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models. Expand
Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
TLDR
This paper proposes to use Gated Graph Neural Networks to encode the graph structure of the semantic parse, and shows on two data sets that the graph networks outperform all baseline models that do not explicitly model the structure. Expand
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
TLDR
A sketch-based approach where the sketch contains a dependency graph, so that one prediction can be done by taking into consideration only the previous predictions that it depends on, and it is shown that SQLNet can outperform the prior art by 9% to 13% on the WikiSQL task. Expand
Grammar-based Neural Text-to-SQL Generation
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. Grammar-basedExpand
...
1
2
3
...