We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
CE-SQL: A Single-Table Chinese Text-to-SQL generation with BERT-Based Slot Filling Method.
- Authors
Yuan-Lin Liang; Chih-Yung Chang; Kuo-Chung Yu
- Abstract
Information retrieval from databases is challenging for a non-SQL domain expert. In order to overcome the challenge, Natural Language-to-SQL (NL2SQL) is currently the most popular method to tackle it. The NL2SQL is a task that generates an equivalent SQL query to retrieve the information from the database based on a natural language question. Research related to NL2SQL has provided decent solutions, especially in English. However, there were very few solutions for the Chinese NL2SQL. This research aims to present a solution for NL2SQL in the Chinese Language. This research also presents a framework based on the pre-trained BERT, which consists of multiple deep-learning models that solve different tasks to extract the SQL-related keywords and values. The experimental results show the robustness and flexibility of the method in extracting the values.
- Subjects
CHINESE language; NATURAL languages; INFORMATION retrieval; DATABASES; SQL
- Publication
International Journal of Design, Analysis & Tools for Integrated Circuits & Systems, 2022, Vol 11, Issue 2, p37
- ISSN
2071-2987
- Publication type
Article