Details
| Original language | English |
|---|---|
| Pages (from-to) | 571-597 |
| Number of pages | 27 |
| Journal | Semantic web |
| Volume | 13 |
| Issue number | 3 |
| Publication status | Published - 6 Apr 2022 |
Abstract
Tabular data plays an essential role in many data analytics and machine learning tasks. Typically, tabular data does not possess any machine-readable semantics. In this context, semantic table interpretation is crucial for making data analytics workflows more robust and explainable. This article proposes Tab2KG-a novel method that targets at the interpretation of tables with previously unseen data and automatically infers their semantics to transform them into semantic data graphs. We introduce original lightweight semantic profiles that enrich a domain ontology's concepts and relations and represent domain and table characteristics. We propose a one-shot learning approach that relies on these profiles to map a tabular dataset containing previously unseen instances to a domain ontology. In contrast to the existing semantic table interpretation approaches, Tab2KG relies on the semantic profiles only and does not require any instance lookup. This property makes Tab2KG particularly suitable in the data analytics context, in which data tables typically contain new instances. Our experimental evaluation on several real-world datasets from different application domains demonstrates that Tab2KG outperforms state-of-The-Art semantic table interpretation baselines.
Keywords
- domain knowledge graphs, one-shot learning, semantic profiles, Semantic table interpretation
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Semantic web, Vol. 13, No. 3, 06.04.2022, p. 571-597.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Tab2KG
T2 - Semantic table interpretation with lightweight semantic profiles
AU - Gottschalk, Simon
AU - Demidova, Elena
N1 - Funding Information: This work is partially funded by the DFG, German Research Foundation (“WorldKG”, 424985896), the Federal Ministry of Education and Research (BMBF), Germany (“Simple-ML”, 01IS18054) and the European Commission (EU H2020, “smashHit”, 871477).
PY - 2022/4/6
Y1 - 2022/4/6
N2 - Tabular data plays an essential role in many data analytics and machine learning tasks. Typically, tabular data does not possess any machine-readable semantics. In this context, semantic table interpretation is crucial for making data analytics workflows more robust and explainable. This article proposes Tab2KG-a novel method that targets at the interpretation of tables with previously unseen data and automatically infers their semantics to transform them into semantic data graphs. We introduce original lightweight semantic profiles that enrich a domain ontology's concepts and relations and represent domain and table characteristics. We propose a one-shot learning approach that relies on these profiles to map a tabular dataset containing previously unseen instances to a domain ontology. In contrast to the existing semantic table interpretation approaches, Tab2KG relies on the semantic profiles only and does not require any instance lookup. This property makes Tab2KG particularly suitable in the data analytics context, in which data tables typically contain new instances. Our experimental evaluation on several real-world datasets from different application domains demonstrates that Tab2KG outperforms state-of-The-Art semantic table interpretation baselines.
AB - Tabular data plays an essential role in many data analytics and machine learning tasks. Typically, tabular data does not possess any machine-readable semantics. In this context, semantic table interpretation is crucial for making data analytics workflows more robust and explainable. This article proposes Tab2KG-a novel method that targets at the interpretation of tables with previously unseen data and automatically infers their semantics to transform them into semantic data graphs. We introduce original lightweight semantic profiles that enrich a domain ontology's concepts and relations and represent domain and table characteristics. We propose a one-shot learning approach that relies on these profiles to map a tabular dataset containing previously unseen instances to a domain ontology. In contrast to the existing semantic table interpretation approaches, Tab2KG relies on the semantic profiles only and does not require any instance lookup. This property makes Tab2KG particularly suitable in the data analytics context, in which data tables typically contain new instances. Our experimental evaluation on several real-world datasets from different application domains demonstrates that Tab2KG outperforms state-of-The-Art semantic table interpretation baselines.
KW - domain knowledge graphs
KW - one-shot learning
KW - semantic profiles
KW - Semantic table interpretation
UR - http://www.scopus.com/inward/record.url?scp=85129166755&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2302.01150
DO - 10.48550/arXiv.2302.01150
M3 - Article
AN - SCOPUS:85129166755
VL - 13
SP - 571
EP - 597
JO - Semantic web
JF - Semantic web
SN - 1570-0844
IS - 3
ER -