Write a Blog >>
SPLASH 2017
Sun 22 - Fri 27 October 2017 Vancouver, Canada
Wed 25 Oct 2017 16:14 - 16:37 at Regency A - Synthesis Chair(s): Jonathan Edwards

This paper presents a new technique for automatically synthesizing SQL queries from natural language (NL). At the core of our technique is 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. Starting with a program sketch obtained using standard parsing techniques, our approach involves an iterative refinement loop that alternates between probabilistic type inhabitation and automated sketch repair. We use the proposed idea to build an end-to-end system called SQLIZER that can synthesize SQL queries from natural language. Our method is fully automated, works for any database without requiring additional customization, and does not require users to know the underlying database schema. We evaluate our approach on over 450 natural language queries concerning three different databases, namely MAS, IMDB, and YELP. Our experiments show that the desired query is ranked within the top 5 candidates in close to 90% of the cases and that SQLIZER outperforms NALIR, a state-of-the-art tool that won a best paper award at VLDB'14.

Wed 25 Oct

Displayed time zone: Tijuana, Baja California change

15:30 - 17:22
SynthesisOOPSLA at Regency A
Chair(s): Jonathan Edwards
15:30
22m
Talk
Model-Assisted Machine-Code Synthesis
OOPSLA
Venkatesh Srinivasan University of Wisconsin - Madison, Ara Vartanian University of Wisconsin-Madison, USA, Thomas Reps University of Wisconsin - Madison and GrammaTech, Inc.
DOI
15:52
22m
Talk
Synthesis of Data Completion Scripts using Finite Tree Automata
OOPSLA
Xinyu Wang UT Austin, Isil Dillig UT Austin, Rishabh Singh Microsoft Research
DOI
16:14
22m
Talk
SQLizer: Query Synthesis from Natural Language
OOPSLA
Navid Yaghmazadeh University of Texas, Austin, Yuepeng Wang University of Texas at Austin, Isil Dillig UT Austin, Thomas Dillig
DOI
16:37
22m
Talk
Synthesizing Configuration File Specifications with Association Rule Learning
OOPSLA
Mark Santolucito Yale University, Ennan Zhai Yale University, USA, Rahul Dhodapkar MongoDB, USA, Aaron Shim Microsoft, USA, Ruzica Piskac Yale University
DOI
16:59
22m
Talk
Natural Synthesis of Provably-Correct Data-Structure Manipulations
OOPSLA
Xiaokang Qiu Purdue University, Armando Solar-Lezama MIT CSAIL
DOI