Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing

We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing. BRIDGE represents the question and DB schema in a tagged sequence where a subset of the fields are augmented with cell values mentioned in the question. The hybrid sequence is encoded by BERT with minimal subsequent layers and the text-DB contextualization is realized via the fine-tuned deep attention in BERT. Combined with a pointer-generator decoder with schema-consistency driven search space pruning, BRIDGE attained state-of-the-art performance on the well-studied Spider benchmark (65.5% dev, 59.2% test), despite being much simpler than most recently proposed models for this task. Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks. Our model implementation is available at https://github.com/ salesforce/TabularSemanticParsing.

[1]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[2]  Michael D. Ernst,et al.  NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System , 2018, LREC.

[3]  Po-Sen Huang,et al.  Execution-Guided Neural Program Decoding , 2018, ArXiv.

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

[5]  Peter Thanisch,et al.  Natural language interfaces to databases – an introduction , 1995, Natural Language Engineering.

[6]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[7]  Peter Rob,et al.  Database systems : design, implementation, and management , 2000 .

[8]  Souvik Kundu,et al.  Hybrid Ranking Network for Text-to-SQL , 2020, ArXiv.

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

[10]  Steven C. H. Hoi,et al.  Photon: A Robust Cross-Domain Text-to-SQL System , 2020, ACL.

[11]  Karen Spärck Jones,et al.  Natural language interfaces to databases , 1990, The Knowledge Engineering Review.

[12]  Peter Rob,et al.  Database systems - design, implementation, and management (2. ed.) , 1995 .

[13]  Seunghyun Park,et al.  A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization , 2019, ArXiv.

[14]  Wen-tau Yih,et al.  An Imitation Game for Learning Semantic Parsers from User Interaction , 2020, EMNLP.

[15]  Xiaodong Liu,et al.  Multi-Task Deep Neural Networks for Natural Language Understanding , 2019, ACL.

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

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

[18]  Jonathan Berant,et al.  Span-based Semantic Parsing for Compositional Generalization , 2020, ArXiv.

[19]  Xiaodong Liu,et al.  RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers , 2019, ACL.

[20]  Omer Levy,et al.  SpanBERT: Improving Pre-training by Representing and Predicting Spans , 2019, TACL.

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

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

[23]  Dong Ryeol Shin,et al.  RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases , 2020, CL.

[24]  Zhifang Sui,et al.  Towards Comprehensive Description Generation from Factual Attribute-value Tables , 2019, ACL.

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

[26]  Arman Cohan,et al.  Longformer: The Long-Document Transformer , 2020, ArXiv.

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

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

[29]  Jonathan Berant,et al.  SmBoP: Semi-autoregressive Bottom-up Semantic Parsing , 2020, ArXiv.

[30]  Lifu Tu,et al.  An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models , 2020, Transactions of the Association for Computational Linguistics.

[31]  Ming-Wei Chang,et al.  Exploring Unexplored Generalization Challenges for Cross-Database Semantic Parsing , 2020, ACL.

[32]  Chen Liang,et al.  Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing , 2018, NeurIPS.

[33]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

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

[35]  Ming-Wei Chang,et al.  Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both? , 2020, ACL.

[36]  Yang Zhang,et al.  Mention Extraction and Linking for SQL Query Generation , 2020, EMNLP.

[37]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[38]  Thomas Muller,et al.  TaPas: Weakly Supervised Table Parsing via Pre-training , 2020, ACL.

[39]  Marc van Zee,et al.  Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures , 2020, ArXiv.

[40]  Graham Neubig,et al.  TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data , 2020, ACL.

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

[42]  Ashish Vaswani,et al.  Self-Attention with Relative Position Representations , 2018, NAACL.

[43]  Tong Guo,et al.  Content Enhanced BERT-based Text-to-SQL Generation , 2019, ArXiv.

[44]  Jesse Vig,et al.  A Multiscale Visualization of Attention in the Transformer Model , 2019, ACL.

[45]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[46]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[47]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[48]  Ian S. Dunn,et al.  Exploring the Limits , 2009 .

[49]  Kaushik Chakrabarti,et al.  X-SQL: reinforce schema representation with context , 2019, ArXiv.

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

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

[52]  Xifeng Yan,et al.  What It Takes to Achieve 100 Percent Condition Accuracy on WikiSQL , 2018, EMNLP.

[53]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[54]  Philip Massey,et al.  Generating Logical Forms from Graph Representations of Text and Entities , 2019, ACL.

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

[56]  Andrew McCallum,et al.  Linguistically-Informed Self-Attention for Semantic Role Labeling , 2018, EMNLP.