1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25368
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSima, Ana Claudia-
dc.contributor.authorMendes de Farias, Tarcisio-
dc.contributor.authorAnisimova, Maria-
dc.contributor.authorDessimoz, Christophe-
dc.contributor.authorRobinson-Rechavi, Marc-
dc.contributor.authorZbinden, Erich-
dc.contributor.authorStockinger, Kurt-
dc.date.accessioned2022-07-27T09:30:39Z-
dc.date.available2022-07-27T09:30:39Z-
dc.date.issued2022-07-
dc.identifier.issn0926-8782de_CH
dc.identifier.issn1573-7578de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/25368-
dc.description.abstractThe 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.de_CH
dc.language.isoende_CH
dc.publisherSpringerde_CH
dc.relation.ispartofDistributed and Parallel Databasesde_CH
dc.rightshttp://creativecommons.org/licenses/by/4.0/de_CH
dc.subjectQuestion answeringde_CH
dc.subjectKnowledge graphde_CH
dc.subjectRankingde_CH
dc.subject.ddc005: Computerprogrammierung, Programme und Datende_CH
dc.titleBio-SODA UX : enabling natural language question answering over knowledge graphs with user disambiguationde_CH
dc.typeBeitrag in wissenschaftlicher Zeitschriftde_CH
dcterms.typeTextde_CH
zhaw.departementLife Sciences und Facility Managementde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Informatik (InIT)de_CH
zhaw.organisationalunitInstitut für Computational Life Sciences (ICLS)de_CH
dc.identifier.doi10.1007/s10619-022-07414-wde_CH
dc.identifier.doi10.21256/zhaw-25368-
zhaw.funding.euNode_CH
zhaw.issue2de_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end440de_CH
zhaw.pages.start409de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume40de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.funding.snf167149de_CH
zhaw.webfeedComputational Genomicsde_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedData Management & Visualisationde_CH
zhaw.webfeedInformation Engineeringde_CH
zhaw.funding.zhawBio-SODA – Enabling Complex, Semantic Queries to Bioinformatics Databases through Intuitive Searching over Data (SNSF NRP 75 "Big Data")de_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen Life Sciences und Facility Management
Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Sima-etal_Bio-SODA-UX.pdf2.03 MBAdobe PDFThumbnail
View/Open
Show simple item record
Sima, A. C., Mendes de Farias, T., Anisimova, M., Dessimoz, C., Robinson-Rechavi, M., Zbinden, E., & Stockinger, K. (2022). Bio-SODA UX : enabling natural language question answering over knowledge graphs with user disambiguation. Distributed and Parallel Databases, 40(2), 409–440. https://doi.org/10.1007/s10619-022-07414-w
Sima, A.C. et al. (2022) ‘Bio-SODA UX : enabling natural language question answering over knowledge graphs with user disambiguation’, Distributed and Parallel Databases, 40(2), pp. 409–440. Available at: https://doi.org/10.1007/s10619-022-07414-w.
A. C. Sima et al., “Bio-SODA UX : enabling natural language question answering over knowledge graphs with user disambiguation,” Distributed and Parallel Databases, vol. 40, no. 2, pp. 409–440, Jul. 2022, doi: 10.1007/s10619-022-07414-w.
SIMA, Ana Claudia, Tarcisio MENDES DE FARIAS, Maria ANISIMOVA, Christophe DESSIMOZ, Marc ROBINSON-RECHAVI, Erich ZBINDEN und Kurt STOCKINGER, 2022. Bio-SODA UX : enabling natural language question answering over knowledge graphs with user disambiguation. Distributed and Parallel Databases. Juli 2022. Bd. 40, Nr. 2, S. 409–440. DOI 10.1007/s10619-022-07414-w
Sima, Ana Claudia, Tarcisio Mendes de Farias, Maria Anisimova, Christophe Dessimoz, Marc Robinson-Rechavi, Erich Zbinden, and Kurt Stockinger. 2022. “Bio-SODA UX : Enabling Natural Language Question Answering over Knowledge Graphs with User Disambiguation.” Distributed and Parallel Databases 40 (2): 409–40. https://doi.org/10.1007/s10619-022-07414-w.
Sima, Ana Claudia, et al. “Bio-SODA UX : Enabling Natural Language Question Answering over Knowledge Graphs with User Disambiguation.” Distributed and Parallel Databases, vol. 40, no. 2, July 2022, pp. 409–40, https://doi.org/10.1007/s10619-022-07414-w.


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