Research paper

SchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL Linking

Published by Association for Computational LinguisticsOct 2026PDF

See how representing schemas as tokens can help link plain-language questions to the correct database elements.

SchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL Linking cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Weibin Liao, Jingwen Liu, Rihong Qiu, Xin Gao, Xinyu Ma, Hongxin Ding, Yue Fang, Yifan Zhu, Yuheng Huang, Junfeng Zhao, Yasha Wang. SchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL Linking. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/2026.emnlp-main.2019. Original PDF, unmodified.

CC BY 4.0

SchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL Linking

Related research.

ADEPT-SQL: A High-performance Text-to-SQL Application for Real-World Enterprise-Level Databases

Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback

LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL