Cargando…
Improving Text-to-SQL with a Hybrid Decoding Method
Text-to-SQL is a task that converts natural language questions into SQL queries. Recent text-to-SQL models employ two decoding methods: sketch-based and generation-based, but each has its own shortcomings. The sketch-based method has limitations in performance as it does not reflect the relevance be...
Autores principales: | Jeong, Geunyeong, Han, Mirae, Kim, Seulgi, Lee, Yejin, Lee, Joosang, Park, Seongsik, Kim, Harksoo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10048569/ https://www.ncbi.nlm.nih.gov/pubmed/36981401 http://dx.doi.org/10.3390/e25030513 |
Ejemplares similares
-
Improving Document-Level Sentiment Classification Using Importance of Sentences
por: Choi, Gihyeon, et al.
Publicado: (2020) -
DETEXA: declarative extensible text exploration and analysis through SQL
por: Foufoulas, Yannis, et al.
Publicado: (2023) -
Refactoring Legacy T-SQL for Improved Performance: Modern Practices for SQL Server Applications
por: Bohm, Lisa
Publicado: (2020) -
SQL Server T-SQL recipes
por: Brimhall, Jason, et al.
Publicado: (2015) -
MySQL and mSQL
por: Yarger, Randy Jay, et al.
Publicado: (1999)