INODE4StatBot.swiss – Application of new algorithms for automatic natural language translation into database query language SQL (NL-to-SQL)
At a glance
- Project leader : Prof. Dr. Kurt Stockinger
- Project team : Patrick Arnecke, Philipp Bosch, Dr. Christine Chorat, Dr. Raphael Defondeville, Oleksii Haievskyi, Dr. Farhad Nooralahzadeh, Ellery Smith, Yi Zhang
- Project budget : CHF 280'000
- Project status : completed
- Funding partner : Federal government (Bundesamt für Statistik BFS)
- Project partner : Bundesamt für Statistik BFS, Kanton Zürich / Statistisches Amt
- Contact person : Kurt Stockinger
Description
The goal of this project is to apply the major algorithms developed in the EU-Project INODE (Intelligent Open Data Exploration, www.inode-project.eu) to Swiss Open Data. The focus is on developing multi-lingual extensions for so-called Natural Language to SQL systems (NL-to-SQL) where a natural language question is automatically translated into the database query language SQL using artificial intelligence solutions such as transformers, i.e. advanced neural networks. The main idea is to enable users to access databases with the major languages spoken in Switzerland.
Publications
-
Nooralahzadeh, Farhad; Zhang, Yi; Smith, Ellery; Maennel, Sabine; Matthey-Doret, Cyril; Raphaël, de Fondville; Stockinger, Kurt,
2024.
StatBot.Swiss : bilingual open data exploration in natural language [paper].
In:
Findings of the Association for Computational Linguistics: ACL 2024.
62nd Annual Meeting of the Association for Computational Linguistics (ACL), Bangkok, Thailand, 11-16 August 2024.
Association for Computational Linguistics.
Available from: https://doi.org/10.21256/zhaw-30993