No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph

Singh, Kuldeep; Lytra, Ioanna; Radhakrishna, Arun Sethupat; Shekarpour, Saeedeh; Vidal, María-Esther; Lehmann, Jens

doi:10.48550/arxiv.1809.10044

Cited by 2 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we tested Sparklis [33], a generic query builder system for knowledge graphs 13 . Furthermore, we compared against GFMed [24] which was top ranked in the QALD4 biomedical challenge and specifically designed for this dataset.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

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

Sima

Farias

Anisimova

et al. 2022

Distrib Parallel Databases

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

“…A growing ecosystem of tools is therefore becoming available for solving subtasks of the KGQA problem, such as entity linking [8][9][10][11] or query generation [12]. However, most of these tools are specifically targeted at question answering over DBpedia [13], not having been applied to other contexts, such as for scientific datasets.…”

Section: Introductionmentioning

confidence: 99%

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

Sima

Farias

Anisimova

et al. 2022

Distrib Parallel Databases

View full text Add to dashboard Cite

show abstract

“…A growing ecosystem of tools is therefore becoming available for solving subtasks of the KGQA problem, such as entity linking [13,26,30,35] or query generation [43]. However, most of these tools are specifically targeted at question answering over DBpedia [37], which casts doubts on their applicability to other contexts, such as for scientific datasets.…”

Section: Introductionmentioning

confidence: 99%

Bio-SODA: Enabling Natural Language Question Answering over Knowledge Graphs without Training Data

Sima¹,

Farias²,

Anisimova³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph

Cited by 2 publications

References 26 publications

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

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

Bio-SODA: Enabling Natural Language Question Answering over Knowledge Graphs without Training Data

Contact Info

Product

Resources

About