Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-26147| Publication type: | Conference paper |
| Type of review: | Peer review (publication) |
| Title: | Improving NL-to-Query systems through re-ranking of semantic hypothesis |
| Authors: | von Däniken, Pius Deriu, Jan Milan Agirre, Eneko Brunner, Ursin Cieliebak, Mark Stockinger, Kurt |
| et. al: | No |
| DOI: | 10.21256/zhaw-26147 |
| Proceedings: | Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022) |
| Editors of the parent work: | Abbas, Mourad Freihat, Abed Alhakim |
| Page(s): | 57 |
| Pages to: | 67 |
| Conference details: | 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022 |
| Issue Date: | Dec-2022 |
| Publisher / Ed. Institution: | Association for Computational Linguistics |
| Language: | English |
| Subjects: | Machine learning; Natural language processing; Database; User interface |
| Subject (DDC): | 005: Computer programming, programs and data 006: Special computer methods |
| Abstract: | Natural Language-to-Query systems translate a natural language question into a formal query language such as SQL. Typically the translation results in a set of candidate query statements due to the ambiguity of natural language. Hence, an important aspect of NL-to-Query systems is to rank the query statements so that the most relevant query is ranked on top. We propose a novel approach to significantly improve the query ranking and thus the accuracy of such systems. First, we use existing methods to translate the natural language question NL_in into k query statements and rank them. Then we translate each of the k query statements back into a natural language question NL_gen and use the semantic similarity between the original question NL_in and each of the k generated questions NL_gen to re-rank the output. Our experiments on two standard datasets, OTTA and Spider, show that this technique improves even strong state-of-the-art NL-to-Query systems by up to 9 percentage points. A detailed error analysis shows that our method correctly down-ranks queries with missing relations and wrong query types. While this work is focused on NL-to-Query, our method could be applied to any other semantic parsing problems as long as a text generation method is available. |
| URI: | https://aclanthology.org/2022.icnlsp-1.7 https://digitalcollection.zhaw.ch/handle/11475/26147 |
| Fulltext version: | Published version |
| License (according to publishing contract): | CC BY 4.0: Attribution 4.0 International |
| Departement: | School of Engineering |
| Organisational Unit: | Centre for Artificial Intelligence (CAI) Institute of Computer Science (InIT) |
| Published as part of the ZHAW project: | INODE – Intelligent Open Data Exploration (EU Horizon 2020) |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2022_vanDaeniken-etal_Improving-NL-to-Query-Systems_ICNLSP2022.pdf | 478.54 kB | Adobe PDF |  View/Open |
Show full item record
von Däniken, P., Deriu, J. M., Agirre, E., Brunner, U., Cieliebak, M., & Stockinger, K. (2022). Improving NL-to-Query systems through re-ranking of semantic hypothesis [Conference paper]. In M. Abbas & A. A. Freihat (Eds.), Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022) (pp. 57–67). Association for Computational Linguistics. https://doi.org/10.21256/zhaw-26147
von Däniken, P. et al. (2022) ‘Improving NL-to-Query systems through re-ranking of semantic hypothesis’, in M. Abbas and A.A. Freihat (eds) Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022). Association for Computational Linguistics, pp. 57–67. Available at: https://doi.org/10.21256/zhaw-26147.
P. von Däniken, J. M. Deriu, E. Agirre, U. Brunner, M. Cieliebak, and K. Stockinger, “Improving NL-to-Query systems through re-ranking of semantic hypothesis,” in Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022), Dec. 2022, pp. 57–67. doi: 10.21256/zhaw-26147.
VON DÄNIKEN, Pius, Jan Milan DERIU, Eneko AGIRRE, Ursin BRUNNER, Mark CIELIEBAK und Kurt STOCKINGER, 2022. Improving NL-to-Query systems through re-ranking of semantic hypothesis. In: Mourad ABBAS und Abed Alhakim FREIHAT (Hrsg.), Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022) [online]. Conference paper. Association for Computational Linguistics. Dezember 2022. S. 57–67. Verfügbar unter: https://aclanthology.org/2022.icnlsp-1.7
von Däniken, Pius, Jan Milan Deriu, Eneko Agirre, Ursin Brunner, Mark Cieliebak, and Kurt Stockinger. 2022. “Improving NL-to-Query Systems through Re-Ranking of Semantic Hypothesis.” Conference paper. In Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022), edited by Mourad Abbas and Abed Alhakim Freihat, 57–67. Association for Computational Linguistics. https://doi.org/10.21256/zhaw-26147.
von Däniken, Pius, et al. “Improving NL-to-Query Systems through Re-Ranking of Semantic Hypothesis.” Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022), edited by Mourad Abbas and Abed Alhakim Freihat, Association for Computational Linguistics, 2022, pp. 57–67, https://doi.org/10.21256/zhaw-26147.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.