Learning knowledge graph embeddings with type regularizer
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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
2 Mar 2018
|
| In: |
Arxiv
|
| Online Access: | Verlag, Volltext: http://arxiv.org/abs/1706.09278
|
| Author Notes: | Bhushan Kotnis and Vivi Nastase |
| Summary: | 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 hitsN, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer. |
|---|---|
| Item Description: | Gesehen am 02.09.2019 |
| Physical Description: | Online Resource |