Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-18074| Publication type: | Article in scientific journal |
| Type of review: | Peer review (publication) |
| Title: | A comparative survey of recent natural language interfaces for databases |
| Authors: | Affolter, Katrin Stockinger, Kurt Bernstein, Abraham |
| et. al: | No |
| DOI: | 10.1007/s00778-019-00567-8 10.21256/zhaw-18074 |
| Published in: | The VLDB Journal |
| Issue Date: | 28-Aug-2019 |
| Publisher / Ed. Institution: | Springer |
| ISSN: | 1066-8888 0949-877X |
| Language: | English |
| Subjects: | Natural language interfaces; Query processing·; Survey; Database research |
| Subject (DDC): | 005: Computer programming, programs and data |
| Abstract: | Over the last few years, natural language interfaces (NLI) for databases have gained significant traction both in academia and industry. These systems use very different approaches as described in recent survey papers. However, these systems have not been systematically compared against a set of benchmark questions in order to rigorously evaluate their functionalities and expressive power. In this paper, we give an overview over 24 recently developed NLIs for databases. Each of the systems is evaluated using a curated list of ten sample questions to show their strengths and weaknesses. We categorize the NLIs into four groups based on the methodology they are using: keyword-, pattern-, parsing- and grammar-based NLI. Overall, we learned that keyword-based systems are enough to answer simple questions. To solve more complex questions involving subqueries, the system needs to apply some sort of parsing to identify structural dependencies. Grammar-based systems are overall the most powerful ones, but are highly dependent on their manually designed rules. In addition to providing a systematic analysis of the major systems, we derive lessons learned that are vital for designing NLIs that can answer a wide range of user questions. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/18074 |
| Fulltext version: | Published version |
| License (according to publishing contract): | CC BY 4.0: Attribution 4.0 International |
| Departement: | School of Engineering |
| Organisational Unit: | Institute of Computer Science (InIT) |
| Published as part of the ZHAW project: | NatalieDB: Natural Language Interface for Databases |
| Appears in collections: | Publikationen School of Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| AComparativeSurveyOfRecentNaturalLanguageInterfaces_VLDBJ_2019.pdf | 1.41 MB | Adobe PDF |  View/Open |
Show full item record
Affolter, K., Stockinger, K., & Bernstein, A. (2019). A comparative survey of recent natural language interfaces for databases. The VLDB Journal. https://doi.org/10.1007/s00778-019-00567-8
Affolter, K., Stockinger, K. and Bernstein, A. (2019) ‘A comparative survey of recent natural language interfaces for databases’, The VLDB Journal [Preprint]. Available at: https://doi.org/10.1007/s00778-019-00567-8.
K. Affolter, K. Stockinger, and A. Bernstein, “A comparative survey of recent natural language interfaces for databases,” The VLDB Journal, Aug. 2019, doi: 10.1007/s00778-019-00567-8.
AFFOLTER, Katrin, Kurt STOCKINGER und Abraham BERNSTEIN, 2019. A comparative survey of recent natural language interfaces for databases. The VLDB Journal. 28 August 2019. DOI 10.1007/s00778-019-00567-8
Affolter, Katrin, Kurt Stockinger, and Abraham Bernstein. 2019. “A Comparative Survey of Recent Natural Language Interfaces for Databases.” The VLDB Journal, August. https://doi.org/10.1007/s00778-019-00567-8.
Affolter, Katrin, et al. “A Comparative Survey of Recent Natural Language Interfaces for Databases.” The VLDB Journal, Aug. 2019, https://doi.org/10.1007/s00778-019-00567-8.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.