Titre
Bio-SODA: Enabling Natural Language Question Answering over Knowledge Graphs without Training Data
Type
article
Institution
UNIL/CHUV/Unisanté + institutions partenaires
Périodique
33rd International Conference on Scientific and Statistical Database Management
Auteur(s)
Sima, Ana Claudia
Auteure/Auteur
Mendes de Farias, Tarcisio
Auteure/Auteur
Anisimova, Maria
Auteure/Auteur
Dessimoz, Christophe
Auteure/Auteur
Robinson-Rechavi, Marc
Auteure/Auteur
Zbinden, Erich
Auteure/Auteur
Stockinger, Kurt
Auteure/Auteur
Liens vers les personnes
Statut éditorial
Publié
Date de publication
2021-07-06
Peer-reviewed
Oui
Langue
anglais
Notes
Conditions permettant de publier le texte intégral: https://www.acm.org/publications/openaccess#green
Résumé
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, 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.
Sujets
PID Serval
serval:BIB_A6616600154D
URL éditeur
Date de création
2021-07-29T08:30:58.167Z
Date de création dans IRIS
2025-05-20T22:08:19Z
Fichier(s)![Vignette d'image]()
En cours de chargement...
Nom
Sima et al. - 2021 - Bio-SODA Enabling Natural Language Question Answe.pdf
Version du manuscrit
published
Licence
https://iris.unil.ch/disclaimer
Taille
991.86 KB
Format
Adobe PDF
PID Serval
serval:BIB_A6616600154D.P001
URN
urn:nbn:ch:serval-BIB_A6616600154D9
Somme de contrôle
(MD5):d91ff889d792da6b6c50ccd5c35cd059