Please use this identifier to cite or link to this item:
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
Conference details: 5th International Conference on Natural Language and Speech Processing (ICNLSP), online, 16-17 December 2022
Issue Date: Dec-2022
Publisher / Ed. Institution: ZHAW Zürcher Hochschule für Angewandte Wissenschaften
Publisher / Ed. Institution: Winterthur
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.
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 Applied Information Technology (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 SizeFormat 
2022_vanDaeniken-etal_Improving-NL-to-Query-Systems_ICNLSP2022.pdf478.54 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.