Bio-SODA UX: enabling natural language question answering over knowledge graphs with user disambiguation.

Details

Ressource 1Download: 10619_2022_Article_7414.pdf (1990.20 [Ko])
State: Public
Version: Final published version
License: CC BY 4.0
Serval ID
serval:BIB_EE90AD3795B0
Type
Article: article from journal or magazin.
Publication sub-type
Review (review): journal as complete as possible of one specific subject, written based on exhaustive analyses from published work.
Collection
Publications
Institution
Title
Bio-SODA UX: enabling natural language question answering over knowledge graphs with user disambiguation.
Journal
Distributed and parallel databases
Author(s)
Sima A.C., Mendes de Farias T., Anisimova M., Dessimoz C., Robinson-Rechavi M., Zbinden E., Stockinger K.
ISSN
1573-7578 (Electronic)
ISSN-L
0926-8782
Publication state
Published
Issued date
2022
Peer-reviewed
Oui
Volume
40
Number
2-3
Pages
409-440
Language
english
Notes
Publication types: Journal Article
Publication Status: ppublish
Abstract
The problem of natural language processing over structured data has become a growing research field, both within the relational database and the Semantic Web community, with significant efforts involved in question answering over knowledge graphs (KGQA). However, many of these approaches are either specifically targeted at open-domain question answering using DBpedia, or require large training datasets to translate a natural language question to SPARQL in order to query the knowledge graph. Hence, these approaches often cannot be applied directly to complex scientific datasets where no prior training data is available. In this paper, we focus on the challenges of natural language processing over knowledge graphs of scientific datasets. In particular, we introduce Bio-SODA, a natural language processing engine that does not require training data in the form of question-answer pairs for generating SPARQL queries. Bio-SODA uses a generic graph-based approach for translating user questions to a ranked list of SPARQL candidate queries. Furthermore, Bio-SODA uses a novel ranking algorithm that includes node centrality as a measure of relevance for selecting the best SPARQL candidate query. Our experiments with real-world datasets across several scientific domains, including the official bioinformatics Question Answering over Linked Data (QALD) challenge, as well as the CORDIS dataset of European projects, show that Bio-SODA outperforms publicly available KGQA systems by an F1-score of least 20% and by an even higher factor on more complex bioinformatics datasets. Finally, we introduce Bio-SODA UX, a graphical user interface designed to assist users in the exploration of large knowledge graphs and in dynamically disambiguating natural language questions that target the data available in these graphs.
Keywords
Information Systems and Management, Hardware and Architecture, Information Systems, Software, Knowledge graphs, Question answering, Ranking
Pubmed
Web of science
Open Access
Yes
Funding(s)
Swiss National Science Foundation
University of Lausanne
Create date
09/09/2022 14:45
Last modification date
04/04/2023 6:16
Usage data