Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-22000| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | ValueNet : a natural language-to-SQL system that learns from database information |
| Authors: | Brunner, Ursin Stockinger, Kurt |
| et. al: | No |
| DOI: | 10.1109/ICDE51399.2021.00220 10.21256/zhaw-22000 |
| Proceedings: | Proceedings of the 37th ICDE |
| Page(s): | 2177 |
| Pages to: | 2182 |
| Conference details: | 37th International Conference on Data Engineering (ICDE), Chania, Greece, 19-22 April 2021 |
| Issue Date: | Apr-2021 |
| Publisher / Ed. Institution: | IEEE |
| Other identifiers: | arXiv:2006.00888v2 |
| Language: | English |
| Subjects: | NL-to-SQL; Natural language interface; Neural network; Transformer |
| Subject (DDC): | 005: Computer programming, programs and data |
| Abstract: | In this paper we propose ValueNet light and ValueNet - two end-to-end Natural Language-to-SQL systems that incorporate values using the challenging Spider dataset.The main idea of our approach is to use not only metadata information from the underlying database but also information on the base data as input for our neural network architecture. In particular, we propose a novel architecture sketch to extract values from a user question and come up with possible value candidates which are not explicitly mentioned in the question. We then use a neural model based on an encoder-decoder architecture to synthesize the SQL query. Finally, we evaluate our model on the Spider challenge using the Execution Accuracy metric, a more difficult metric than used by most participants of the challenge. Our experimental evaluation demonstrates that ValueNet light and ValueNet reach state-of-the-art results of 67% and 62% accuracy, respectively, for translating from NL to SQL whilst incorporating values. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/22000 |
| Fulltext version: | Accepted version |
| License (according to publishing contract): | Not specified |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Applied Information Technology (InIT) |
| Published as part of the ZHAW project: | INODE - Intelligent Open Data Exploration |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2021_Brunner-Stockinger_ValueNet_ICDE-Paper.pdf | Accepted Version | 585.22 kB | Adobe PDF |  View/Open |
Show full item record
Brunner, U., & Stockinger, K. (2021). ValueNet : a natural language-to-SQL system that learns from database information [Conference paper]. Proceedings of the 37th ICDE, 2177–2182. https://doi.org/10.1109/ICDE51399.2021.00220
Brunner, U. and Stockinger, K. (2021) ‘ValueNet : a natural language-to-SQL system that learns from database information’, in Proceedings of the 37th ICDE. IEEE, pp. 2177–2182. Available at: https://doi.org/10.1109/ICDE51399.2021.00220.
U. Brunner and K. Stockinger, “ValueNet : a natural language-to-SQL system that learns from database information,” in Proceedings of the 37th ICDE, Apr. 2021, pp. 2177–2182. doi: 10.1109/ICDE51399.2021.00220.
BRUNNER, Ursin und Kurt STOCKINGER, 2021. ValueNet : a natural language-to-SQL system that learns from database information. In: Proceedings of the 37th ICDE. Conference paper. IEEE. April 2021. S. 2177–2182
Brunner, Ursin, and Kurt Stockinger. 2021. “ValueNet : A Natural Language-to-SQL System That Learns from Database Information.” Conference paper. In Proceedings of the 37th ICDE, 2177–82. IEEE. https://doi.org/10.1109/ICDE51399.2021.00220.
Brunner, Ursin, and Kurt Stockinger. “ValueNet : A Natural Language-to-SQL System That Learns from Database Information.” Proceedings of the 37th ICDE, IEEE, 2021, pp. 2177–82, https://doi.org/10.1109/ICDE51399.2021.00220.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.