Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing

The task of multi-turn text-to-SQL semantic parsing aims to translate natural language utterances in an interaction into SQL queries in order to answer them using a database which normally contains multiple table schemas. Previous studies on this task usually utilized contextual information to enrich utterance representations and to further influence the decoding process. While they ignored to describe and track the interaction states which are determined by history SQL queries and are related with the intent of current utterance. In this paper, two kinds of interaction states are defined based on schema items and SQL keywords separately. A relational graph neural network and a non-linear layer are designed to update the representations of these two states respectively. The dynamic schema-state and SQL-state representations are then utilized to decode the SQL query corresponding to current utterance. Experimental results on the challenging CoSQL dataset demonstrate the effectiveness of our proposed method, which achieves better performance than other published methods on the task leaderboard.

[1]  Kai Wang,et al.  Multi-Domain Dialogue Acts and Response Co-Generation , 2020, ACL.

[2]  R. Socher,et al.  Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning , 2017, ArXiv.

[3]  Noah A. Smith,et al.  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2016, ACL 2016.

[4]  Graham Neubig,et al.  A Syntactic Neural Model for General-Purpose Code Generation , 2017, ACL.

[5]  Jonathan Berant,et al.  Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing , 2019, ACL.

[6]  Luyao Chen,et al.  CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases , 2019, EMNLP.

[7]  Tao Yu,et al.  SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task , 2018, EMNLP.

[8]  Dawn Xiaodong Song,et al.  SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning , 2017, ArXiv.

[9]  Luke S. Zettlemoyer,et al.  Bootstrapping Semantic Parsers from Conversations , 2011, EMNLP.

[10]  Shujian Huang,et al.  Dialogue State Tracking with Explicit Slot Connection Modeling , 2020, ACL.

[11]  Tao Yu,et al.  TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation , 2018, NAACL.

[12]  Alexander I. Rudnicky,et al.  Expanding the Scope of the ATIS Task: The ATIS-3 Corpus , 1994, HLT.

[13]  Lei Zhang,et al.  Joint Intent Detection and Entity Linking on Spatial Domain Queries , 2020, FINDINGS.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Richard Socher,et al.  Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning , 2018, ArXiv.

[16]  George R. Doddington,et al.  The ATIS Spoken Language Systems Pilot Corpus , 1990, HLT.

[17]  Yoav Artzi,et al.  Learning to Map Context-Dependent Sentences to Executable Formal Queries , 2018, NAACL.

[18]  Yan Gao,et al.  Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation , 2019, ACL.

[19]  Zhen-Hua Ling,et al.  Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots , 2019, EMNLP.

[20]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[21]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[22]  Tsung-Hsien Wen,et al.  Neural Belief Tracker: Data-Driven Dialogue State Tracking , 2016, ACL.

[23]  Ming-Wei Chang,et al.  Search-based Neural Structured Learning for Sequential Question Answering , 2017, ACL.

[24]  Mirella Lapata,et al.  Coarse-to-Fine Decoding for Neural Semantic Parsing , 2018, ACL.

[25]  Richard M. Schwartz,et al.  A Fully Statistical Approach to Natural Language Interfaces , 1996, ACL.

[26]  Ming-Wei Chang,et al.  Driving Semantic Parsing from the World’s Response , 2010, CoNLL.

[27]  Tao Yu,et al.  Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task , 2018, EMNLP.

[28]  Dragomir R. Radev,et al.  Improving Text-to-SQL Evaluation Methodology , 2018, ACL.

[29]  Jayant Krishnamurthy,et al.  Neural Semantic Parsing with Type Constraints for Semi-Structured Tables , 2017, EMNLP.

[30]  Raymond J. Mooney,et al.  Learning to Parse Database Queries Using Inductive Logic Programming , 1996, AAAI/IAAI, Vol. 2.

[31]  David Vandyke,et al.  A Network-based End-to-End Trainable Task-oriented Dialogue System , 2016, EACL.

[32]  Jonathan Berant,et al.  Building a Semantic Parser Overnight , 2015, ACL.

[33]  Zhou Yu,et al.  SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing , 2020, ACL.

[34]  Zhen-Hua Ling,et al.  Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots , 2019, CIKM.

[35]  Tao Yu,et al.  Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions , 2019, EMNLP.

[36]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[37]  Tao Yu,et al.  SParC: Cross-Domain Semantic Parsing in Context , 2019, ACL.

[38]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[39]  Stefan Ultes,et al.  MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling , 2018, EMNLP.

[40]  Jonathan Berant,et al.  Global Reasoning over Database Structures for Text-to-SQL Parsing , 2019, EMNLP.