mlsanityData to 7 Oct 2026

MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL

arXiv 2212.09278 ↗First posted 19 Dec 2022cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most state-of-the-art conversational text- to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs' ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-specific natural language prompts to boost the main task from multi-task training. Later in the fine-tuning stage, we propose four SQL perturbations to alleviate the error propagation problem. MIGA tends to achieve state-of-the-art performance on two benchmarks (SparC and CoSQL). We also provide extensive analyses and discussions to shed light on some new perspectives for conversational text-to-SQL.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

33 of 38 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  9. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  10. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  11. 2018Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Taskscited by 214
  12. 2021Muppet: Massive Multi-task Representations with Pre-Finetuningcited by 192
21 more
  1. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  2. 2018Towards Deep Conversational Recommendationscited by 174
  3. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  4. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
  5. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  6. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  7. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  8. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  9. 2020Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systemscited by 98
  10. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  11. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  12. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  13. 2020How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Contextcited by 53
  14. 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
  15. 2022A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systemscited by 32
  16. 2020IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generationcited by 29
  17. 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
  18. 2020Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsingcited by 18
  19. 2021Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQLcited by 13
  20. 2022CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parserscited by 11
  21. 2021Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQLcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translationcited by 17
  2. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
  3. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQLcited by 11
  4. 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanationscited by 7
  5. 2026Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQLcited by 0