Learning knowledge graph embeddings with type regularizer

• Verfasst von: Kotnis, Bhushan [VerfasserIn]
• Verfasst von: Nastase, Vivi [VerfasserIn]
• Titel: Learning knowledge graph embeddings with type regularizer
• Verf.angabe: Bhushan Kotnis and Vivi Nastase
• E-Jahr: 2018
• Jahr: 2 Mar 2018
• Umfang: 6 S.
• Fussnoten: Gesehen am 02.09.2019
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2018
• Band/Heft Quelle: (2018)
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Forschungsdaten Kotnis, Bhushan: KGE algorithms
• Sach-SW: Computer Science - Artificial Intelligence
• K10plus-PPN: 1675677042

Abstract

Learning relations based on evidence from knowledge bases relies on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. We note increased performance compared to the baseline model in terms of mean reciprocal rank and hits@N, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer.