DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
Published 1 January 2020Open access
Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu
Citations38
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs, and adopts an effective data construction framework via human-computer collaboration.
Abstract
Due to the lack of labeled data, previous research on text-to-SQL parsing mainly focuses on English. Representative English datasets include ATIS, WikiSQL, Spider, etc. This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs. Our new dataset has three major characteristics. First, by manually analyzing questions from several representative applications, we try to figure out the true distribution of SQL queries in real-life needs. Second, DuSQL contains a considerable proportion of SQL queries involving row or column calculations, motivated by our analysis on the SQL query distributions. Finally, we adopt an effective data construction framework via human-computer collaboration. The basic idea is automatically generating SQL queries based on the SQL grammar and constrained by the given database. This paper describes in detail the construction process and data statistics of DuSQL. Moreover, we present and compare performance of several open-source text-to-SQL parsers with minor modification to accommodate Chinese, including a simple yet effective extension to IRNet for handling calculation SQL queries.
Keywords
Computer Science
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
45,681 Citations2018Kefallinos, Dionysios, Alexandris, Georgios +6 more
32,525 Citations2019Jacob Devlin, Ming‐Wei Chang +2 more
A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
arXiv (Cornell University)Analysis of Points of Interests Recommended for Leisure Walk Descriptions
1,291 Citations2024Payal Bajaj, Bui, Thi Minh Hoai +2 more
The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering.
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
831 Citations2018Tao Yu, Rui Zhang +10 more
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.
arXiv (Cornell University)Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
782 Citations2017Victor W. Zhong, Caiming Xiong +1 more
Language to Logical Form with Neural Attention
643 Citations2016Li Dong, Mirella Lapata
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.
A Syntactic Neural Model for General-Purpose Code Generation
535 Citations2017Pengcheng Yin, Graham Neubig
Towards a theory of natural language interfaces to databases
521 Citations2003Ana-Maria Popescu, Oren Etzioni +1 more
This paper proves that, for a broad class of semantically tractable natural language questions, Precise is guaranteed to map each question to the corresponding SQL query, and shows that Precise compares favorably with Mooney's learning NLI and with Microsoft's English Query product.
Proceedings of the VLDB EndowmentConstructing an interactive natural language interface for relational databases
440 Citations2014Li Fei, H. V. Jagadish
The architecture of an interactive natural language query interface for relational databases is described, able to correctly interpret complex natural language queries, in a generic manner across a range of domains, and is good enough to be usable in practice.
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
364 Citations2019Jiaqi Guo, Zecheng Zhan +5 more
The proposed IRNet aims to address two challenges: the mismatch between intents expressed in natural language (NL) and the implementation details in SQL and the challenge in predicting columns caused by the large number of out-of-domain words.
Building a Semantic Parser Overnight
350 Citations2015Yushi Wang, Jonathan Berant +1 more
A new methodology is introduced that uses a simple grammar to generate logical forms paired with canonical utterances that are meant to cover the desired set of compositional operators and uses crowdsourcing to paraphrase these canonical utterance into natural utterances.
AI MagazineQuestion Answering from Frequently Asked Question Files: Experiences with the FAQ Finder System
339 Citations1997Robin Burke, Kristian J. Hammond +4 more
This technical report describes FAQ Finder, a natural language question answering system that uses files of frequently asked questions as its knowledge base, and describes the design and the current implementation of the system and its support components.
Scaling question answering to the Web
327 Citations2001Cody C. T. Kwok, Oren Etzioni +1 more
Mulder is introduced, which is believed to be the first general-purpose, fully-automated question-answering system available on the web, and its architecture is described, which relies on multiple search-engine queries, natural-language parsing, and a novel voting procedure to yield reliable answers coupled with high recall.
arXiv (Cornell University)SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
303 Citations2017Xiaojun Xu, Chang Liu +1 more
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.
Latent Predictor Networks for Code Generation
293 Citations2016Ling Wang, Phil Blunsom +5 more
A novel neural network architecture is presented which generates an output sequence conditioned on an arbitrary number of input functions and allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to be marginalised, thus permitting scalable and effective training.
Proceedings of the ACM on Programming LanguagesSQLizer: query synthesis from natural language
287 Citations2017Navid Yaghmazadeh, Yuepeng Wang +2 more
This paper presents a new technique for automatically synthesizing SQL queries from natural language (NL) using a new NL-based program synthesis methodology that combines semantic parsing techniques from the NLP community with type-directed program synthesis and automated program repair.
Lecture notes in computer scienceUsing Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing
268 Citations2001Lappoon R. Tang, Raymond J. Mooney
Preliminary results demonstrated that an approach which combines different learning methods in inductive logic programming (ILP) to allow a learner to produce more expressive hypotheses than that of each individual learner is promising.
ACM Transactions on Information SystemsScaling question answering to the web
237 Citations2001Cody Kwok, Oren Etzioni +1 more
Improving Text-to-SQL Evaluation Methodology
214 Citations2018Catherine Finegan‐Dollak, Jonathan K. Kummerfeld +5 more
It is shown that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries, and proposes a complementary dataset split for evaluation of future work.
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task
200 Citations2018Tao Yu, Michihiro Yasunaga +5 more
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.
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
187 Citations2019Ben Bogin, Jonathan Berant +1 more
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.
arXiv (Cornell University)Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain\n Semantic Parsing and Text-to-SQL Task
153 Citations2018Changyuan Yu, Rui Zhang +10 more
arXiv (Cornell University)Lambda Dependency-Based Compositional Semantics
122 Citations2013Percy Liang
This short note presents a new formal language, lambda dependency-based compositional semantics (lambda DCS) for representing logical forms in semantic parsing by eliminating variables and making existential quantification implicit.
Semantic Parsing with Syntax- and Table-Aware SQL Generation
75 Citations2018Yibo Sun, Duyu Tang +7 more
The quality of the generated SQL query is significantly improved through learning to replicate content from column names, cells or SQL keywords; and improving the generation of WHERE clause by leveraging the column-cell relation.
arXiv (Cornell University)RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL\n Parsers
72 Citations2019Bailin Wang, Richard Shin +3 more
arXiv (Cornell University)X-SQL: reinforce schema representation with context
53 Citations2019Pengcheng He, Yi Mao +2 more
X-SQL is presented, a new network architecture for the problem of parsing natural language to SQL query that proposes to enhance the structural schema representation with the contextual output from BERT-style pre-training model and together with type information to learn a new schema representation for down-stream tasks.
A Pilot Study for Chinese SQL Semantic Parsing
51 Citations2019Qingkai Min, Yuefeng Shi +1 more
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.
arXiv (Cornell University)Content Enhanced BERT-based Text-to-SQL Generation
45 Citations2019Tong Guo, Huilin Gao
This work presents a simple methods to leverage the table content for the BERT-based model to solve the text-to-SQL problem and encodes two addition feature vector for the deep model.
arXiv (Cornell University)SyntaxSQLNet: Syntax Tree Networks for Complex and\n Cross-DomainText-to-SQL Task
35 Citations2018Changyuan Yu, Michihiro Yasunaga +5 more
Towards a theory of natural language interfaces to databases
23 Citations2003Ana-Maria Popescu, Oren Etzioni +1 more
arXiv (Cornell University)TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation
14 Citations2020Ningyuan Sun, Xuefeng Yang +1 more
TableQA is presented, a large-scale cross-domain Natural Language to SQL dataset in Chinese language consisting 64,891 questions and 20,311 unique SQL queries on over 6,000 tables that requires to generalize well not only to SQL skeletons of different questions and table schemas, but also to the various expressions for condition values.