Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-26147
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | von Däniken, Pius | - |
dc.contributor.author | Deriu, Jan Milan | - |
dc.contributor.author | Agirre, Eneko | - |
dc.contributor.author | Brunner, Ursin | - |
dc.contributor.author | Cieliebak, Mark | - |
dc.contributor.author | Stockinger, Kurt | - |
dc.date.accessioned | 2022-11-18T14:48:44Z | - |
dc.date.available | 2022-11-18T14:48:44Z | - |
dc.date.issued | 2022-12 | - |
dc.identifier.uri | https://digitalcollection.zhaw.ch/handle/11475/26147 | - |
dc.description.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. | de_CH |
dc.language.iso | en | de_CH |
dc.publisher | ZHAW Zürcher Hochschule für Angewandte Wissenschaften | de_CH |
dc.rights | http://creativecommons.org/licenses/by/4.0/ | de_CH |
dc.subject | Machine learning | de_CH |
dc.subject | Natural language processing | de_CH |
dc.subject | Database | de_CH |
dc.subject | User interface | de_CH |
dc.subject.ddc | 005: Computerprogrammierung, Programme und Daten | de_CH |
dc.subject.ddc | 006: Spezielle Computerverfahren | de_CH |
dc.title | Improving NL-to-Query systems through re-ranking of semantic hypothesis | de_CH |
dc.type | Konferenz: Paper | de_CH |
dcterms.type | Text | de_CH |
zhaw.departement | School of Engineering | de_CH |
zhaw.organisationalunit | Centre for Artificial Intelligence (CAI) | de_CH |
zhaw.organisationalunit | Institut für Informatik (InIT) | de_CH |
zhaw.publisher.place | Winterthur | de_CH |
dc.identifier.doi | 10.21256/zhaw-26147 | - |
zhaw.conference.details | 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022 | de_CH |
zhaw.funding.eu | info:eu-repo/grantAgreement/EC/H2020/863410//INODE - Intelligent Open Data Exploration/INODE | de_CH |
zhaw.originated.zhaw | Yes | de_CH |
zhaw.publication.status | publishedVersion | de_CH |
zhaw.publication.review | Peer review (Publikation) | de_CH |
zhaw.webfeed | Intelligent Information Systems | de_CH |
zhaw.webfeed | Natural Language Processing | de_CH |
zhaw.funding.zhaw | INODE – Intelligent Open Data Exploration (EU Horizon 2020) | de_CH |
zhaw.author.additional | No | de_CH |
zhaw.display.portrait | Yes | de_CH |
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 simple item record
von Däniken, P., Deriu, J. M., Agirre, E., Brunner, U., Cieliebak, M., & Stockinger, K. (2022, December). Improving NL-to-Query systems through re-ranking of semantic hypothesis. 5th International Conference on Natural Language and Speech Processing (ICNLSP), Online, 16-17 December 2022. 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 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022. Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften. 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 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022, Dec. 2022. 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: 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022. Conference paper. Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften. Dezember 2022
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 5th International Conference on Natural Language and Speech Processing (ICNLSP), Online, 16-17 December 2022. Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-26147.
von Däniken, Pius, et al. “Improving NL-to-Query Systems through Re-Ranking of Semantic Hypothesis.” 5th International Conference on Natural Language and Speech Processing (ICNLSP), Online, 16-17 December 2022, ZHAW Zürcher Hochschule für Angewandte Wissenschaften, 2022, https://doi.org/10.21256/zhaw-26147.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.