SQLizer: query synthesis from natural language

By Navid Yaghmazadeh, Yuepeng Wang, Işıl Dillig, Thomas Dillig. 2017

336 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Software, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Software

In Natural Language Processing

Citations in the corpus

SPoC: Search-based Pseudocode to Code (2019, background): “One of its traditional tasks is to parse a given question (usually a single sentence) into an executable database query [42, 43, 20, 4, 44, 39].”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, methodology): “Yaghmazadeh et al. (2017) use S EMPRE (Berant et al., 2013) to map a sentence into SQL sketches which are completed using program synthesis techniques and iteratively repaired if they are faulty.”
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2019, background): “, 2017), Academic (Li and Jagadish, 2014), Yelp and IMDB (Yaghmazadeh et al., 2017) datasets.”
Natural language to SQL: Where are we today? (2020, methodology): “SQLizer [43] parses q nl into a logical form using Sem-pre [30], then iteratively reﬁnes the form.”
ChartDialogs: Plotting from Natural Language Instructions (2020, background): “Natural language interfaces to structured languages such as SQL have been explored in Databases (DB) (Li and Jagadish, 2014), Programming Languages (PL) (Yaghmazadeh et al., 2017), and NLP (Zelle and Mooney, 1996).”
Semantic Evaluation for Text-to-SQL with Distilled Test Suite (2020, background): “However, we also generated distilled test suites for other popular text-to-SQL datasets including C o SQL (Yu et al., 2019a), SP ar C (Yu et al., 2019b), Academic (Li and Jagadish, 2014), Advising (Finegan-Dollak et al., 2018a), ATIS (Dahl et al., 1994), Geography (Zelle and Mooney, 1996), IMDB (Yag”
Synchromesh: Reliable code generation from pre-trained language models (2022, background): “In particular, synthesis from natural language descriptions has gained recent attention (Liu et al., 2016; Yaghmazadeh et al., 2017), thanks to advances in natural language processing models such as Transformers (Vaswani et al., 2017).”
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (2019, background): “Interested readers can refer to Yin and Neubig (2017) for details of the action APPLYRULE.”
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions (2021, methodology): “Benchmarks such as Academic (Li and Jagadish, 2014), IMDB and Yelp (Yaghmazadeh et al., 2017) are too small scale and only contain fewer than 200 questions.”
CodeS: Towards Building Open-source Language Models for Text-to-SQL (2024, neutral): “Spider contains 200 databases that cover 138 diverse domains.”
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning (2017, methodology): “Since SQLizer does not require database-speciﬁc training and its code is not available, it is unclear how SQLizer will perform on the WikiSQL task.”
TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation (2018, methodology): “The methods of the Database community (Li and Jagadish, 2014; Yaghmazadeh et al., 2017) involve more hand feature engineering and user interactions with the systems.”
Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases (2019, methodology): “Any post-processing, such as the hand-written repair rules in [41] or soliciting additional user interaction as in [22] may also be performed at this point.”
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (2023, background): “Text-to-SQL parsing [55, 50, 51, 3, 52, 37], which focuses on converting natural language questions into SQL queries, has attracted significant research interests from both academia and industry.”
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, background): “However, most NL query systems expect the query to be well-formed and stated in a single sentence (Zelle and Mooney, 1996; Li and Jagadish, 2014; Yaghmazadeh et al., 2017; Iyer et al., 2017; Zhong et al., 2017; Xu et al., 2017; Shi et al., 2018; Wang et al., 2018; Yu et al., 2018b,c).”
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing (2021, background): “…language sentence into a logical form, known as semantic parsing, is a fundamental problem in natural language processing (Zelle and Mooney 1996; Zettlemoyer and Collins 2005; Wong and Mooney 2007; Zettlemoyer and Collins 2007; Li and Jagadish 2014; Yaghmazadeh et al. 2017; Iyer et al. 2017).”
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task (2018, methodology): “…data, their training split includes 752 queries and 1659 questions from six existing datasets: Restaurants (Tang and Mooney, 2001; Popescu et al., 2003b), GeoQuery (Zelle and Mooney, 1996), Scholar (Iyer et al., 2017), Academic (Li and Jagadish, 2014), Yelp and IMDB (Yaghmazadeh et al., 2017).”
AutoPandas: neural-backed generators for program synthesis (2019, methodology): “…2011; Parisotto et al. 2017], data wrangling [Feng et al. 2018, 2017; Le and Gulwani 2014], data processing [Smith and Albarghouthi 2016; Yaghmazadeh et al. 2018], syntax transformations [Rolim et al. 2017], database queries [Yaghmazadeh et al. 2017] and bit-vector manipulations [Jha et al. 2010].”