Details
| Original language | English |
|---|---|
| Title of host publication | Web Information Systems Engineering – WISE 2020 |
| Subtitle of host publication | 21st International Conference, Amsterdam, The Netherlands, October 20–24, 2020, Proceedings, Part I |
| Editors | Zhisheng Huang, Wouter Beek, Hua Wang, Yanchun Zhang, Rui Zhou |
| Pages | 328-342 |
| Number of pages | 15 |
| ISBN (electronic) | 978-3-030-62005-9 |
| Publication status | Published - 2020 |
| Externally published | Yes |
| Event | 21st International Conference on Web Information Systems Engineering - Amsterdam, Netherlands Duration: 20 Oct 2020 → 24 Oct 2020 Conference number: 21 |
Publication series
| Name | Lecture Notes in Computer Science |
|---|---|
| Volume | 12342 |
| ISSN (Print) | 0302-9743 |
| ISSN (electronic) | 1611-3349 |
Abstract
The collaborative knowledge graphs such as Wikidata excessively rely on the crowd to author the information. Since the crowd is not bound to a standard protocol for assigning entity titles, the knowledge graph is populated by non-standard, noisy, long or even sometimes awkward titles. The issue of long, implicit, and nonstandard entity representations is a challenge in Entity Linking (EL) approaches for gaining high precision and recall. Underlying KG in general is the source of target entities for EL approaches, however, it often contains other relevant information, such as aliases of entities (e.g., Obama and Barack Hussein Obama are aliases for the entity Barack Obama). EL models usually ignore such readily available entity attributes. In this paper, we examine the role of knowledge graph context on an attentive neural network approach for entity linking on Wikidata. Our approach contributes by exploiting the sufficient context from a KG as a source of background knowledge, which is then fed into the neural network. This approach demonstrates merit to address challenges associated with entity titles (multi-word, long, implicit, case-sensitive). Our experimental study shows 8% improvements over the baseline approach, and significantly outperform an end to end approach for Wikidata entity linking.
Keywords
- cs.CL, Entity linking, Wikidata, Knowledge graph context
ASJC Scopus subject areas
- Mathematics(all)
- Theoretical Computer Science
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Web Information Systems Engineering – WISE 2020: 21st International Conference, Amsterdam, The Netherlands, October 20–24, 2020, Proceedings, Part I. ed. / Zhisheng Huang; Wouter Beek; Hua Wang; Yanchun Zhang; Rui Zhou. 2020. p. 328-342 (Lecture Notes in Computer Science; Vol. 12342).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Encoding Knowledge Graph Entity Aliases in Attentive Neural Network for Wikidata Entity Linking
AU - Mulang, Isaiah Onando
AU - Singh, Kuldeep
AU - Vyas, Akhilesh
AU - Shekarpour, Saeedeh
AU - Vidal, Maria Esther
AU - Lehmann, Jens
AU - Auer, Sören
N1 - Conference code: 21
PY - 2020
Y1 - 2020
N2 - The collaborative knowledge graphs such as Wikidata excessively rely on the crowd to author the information. Since the crowd is not bound to a standard protocol for assigning entity titles, the knowledge graph is populated by non-standard, noisy, long or even sometimes awkward titles. The issue of long, implicit, and nonstandard entity representations is a challenge in Entity Linking (EL) approaches for gaining high precision and recall. Underlying KG in general is the source of target entities for EL approaches, however, it often contains other relevant information, such as aliases of entities (e.g., Obama and Barack Hussein Obama are aliases for the entity Barack Obama). EL models usually ignore such readily available entity attributes. In this paper, we examine the role of knowledge graph context on an attentive neural network approach for entity linking on Wikidata. Our approach contributes by exploiting the sufficient context from a KG as a source of background knowledge, which is then fed into the neural network. This approach demonstrates merit to address challenges associated with entity titles (multi-word, long, implicit, case-sensitive). Our experimental study shows 8% improvements over the baseline approach, and significantly outperform an end to end approach for Wikidata entity linking.
AB - The collaborative knowledge graphs such as Wikidata excessively rely on the crowd to author the information. Since the crowd is not bound to a standard protocol for assigning entity titles, the knowledge graph is populated by non-standard, noisy, long or even sometimes awkward titles. The issue of long, implicit, and nonstandard entity representations is a challenge in Entity Linking (EL) approaches for gaining high precision and recall. Underlying KG in general is the source of target entities for EL approaches, however, it often contains other relevant information, such as aliases of entities (e.g., Obama and Barack Hussein Obama are aliases for the entity Barack Obama). EL models usually ignore such readily available entity attributes. In this paper, we examine the role of knowledge graph context on an attentive neural network approach for entity linking on Wikidata. Our approach contributes by exploiting the sufficient context from a KG as a source of background knowledge, which is then fed into the neural network. This approach demonstrates merit to address challenges associated with entity titles (multi-word, long, implicit, case-sensitive). Our experimental study shows 8% improvements over the baseline approach, and significantly outperform an end to end approach for Wikidata entity linking.
KW - cs.CL
KW - Entity linking
KW - Wikidata
KW - Knowledge graph context
UR - http://www.scopus.com/inward/record.url?scp=85096624316&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-62005-9_24
DO - 10.1007/978-3-030-62005-9_24
M3 - Conference contribution
SN - 978-3-030-62004-2
T3 - Lecture Notes in Computer Science
SP - 328
EP - 342
BT - Web Information Systems Engineering – WISE 2020
A2 - Huang, Zhisheng
A2 - Beek, Wouter
A2 - Wang, Hua
A2 - Zhang, Yanchun
A2 - Zhou, Rui
T2 - 21st International Conference on Web Information Systems Engineering
Y2 - 20 October 2020 through 24 October 2020
ER -