Knowledge Graph Embedding by Dynamic Translation
Knowledge graph embedding aims at representing entities and relations in a knowledge graph as dense, low-dimensional and real-valued vectors. It can efficiently measure semantic correlations of entities and relations in knowledge graphs, and improve the performance of knowledge acquisition, fusion a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2017-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8057770/ |
| _version_ | 1818876764024209408 |
|---|---|
| author | Liang Chang Manli Zhu Tianlong Gu Chenzhong Bin Junyan Qian Ji Zhang |
| author_facet | Liang Chang Manli Zhu Tianlong Gu Chenzhong Bin Junyan Qian Ji Zhang |
| author_sort | Liang Chang |
| collection | DOAJ |
| description | Knowledge graph embedding aims at representing entities and relations in a knowledge graph as dense, low-dimensional and real-valued vectors. It can efficiently measure semantic correlations of entities and relations in knowledge graphs, and improve the performance of knowledge acquisition, fusion and inference. Among various embedding models appeared in recent years, the translation-based models such as TransE, TransH, TransR and TranSparse achieve state-of-the-art performance. However, the translation principle applied in these models is too strict and can not deal with complex entities and relations very well. In this paper, by introducing parameter vectors into the translation principle which treats each relation as a translation from the head entity to the tail entity, we propose a novel dynamic translation principle which supports flexible translation between the embeddings of entities and relations. We use this principle to improve the TransE, TransR and TranSparse models respectively and build new models named TransE-DT, TransR-DT and TranSparse-DT correspondingly. Experimental results show that our dynamic translation principle achieves great improvement in both the link prediction task and the triple classification task. |
| first_indexed | 2024-12-19T13:47:34Z |
| format | Article |
| id | doaj.art-7b306803ef974684a23246c99fe2635e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:47:34Z |
| publishDate | 2017-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7b306803ef974684a23246c99fe2635e2022-12-21T20:18:50ZengIEEEIEEE Access2169-35362017-01-015208982090710.1109/ACCESS.2017.27591398057770Knowledge Graph Embedding by Dynamic TranslationLiang Chang0Manli Zhu1https://orcid.org/0000-0002-8231-5342Tianlong Gu2Chenzhong Bin3Junyan Qian4https://orcid.org/0000-0002-1325-6975Ji Zhang5Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, ChinaGuangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, ChinaGuangxi Experiment Center of Information Science, Guilin University of Electronic Technology, Guilin, ChinaGuangxi Experiment Center of Information Science, Guilin University of Electronic Technology, Guilin, ChinaGuangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, ChinaFaculty of Health, Engineering and Sciences, University of Southern Queensland, Toowoomba, QLD, AustraliaKnowledge graph embedding aims at representing entities and relations in a knowledge graph as dense, low-dimensional and real-valued vectors. It can efficiently measure semantic correlations of entities and relations in knowledge graphs, and improve the performance of knowledge acquisition, fusion and inference. Among various embedding models appeared in recent years, the translation-based models such as TransE, TransH, TransR and TranSparse achieve state-of-the-art performance. However, the translation principle applied in these models is too strict and can not deal with complex entities and relations very well. In this paper, by introducing parameter vectors into the translation principle which treats each relation as a translation from the head entity to the tail entity, we propose a novel dynamic translation principle which supports flexible translation between the embeddings of entities and relations. We use this principle to improve the TransE, TransR and TranSparse models respectively and build new models named TransE-DT, TransR-DT and TranSparse-DT correspondingly. Experimental results show that our dynamic translation principle achieves great improvement in both the link prediction task and the triple classification task.https://ieeexplore.ieee.org/document/8057770/Dynamic translationembeddingsknowledge graphtranslation-based models |
| spellingShingle | Liang Chang Manli Zhu Tianlong Gu Chenzhong Bin Junyan Qian Ji Zhang Knowledge Graph Embedding by Dynamic Translation IEEE Access Dynamic translation embeddings knowledge graph translation-based models |
| title | Knowledge Graph Embedding by Dynamic Translation |
| title_full | Knowledge Graph Embedding by Dynamic Translation |
| title_fullStr | Knowledge Graph Embedding by Dynamic Translation |
| title_full_unstemmed | Knowledge Graph Embedding by Dynamic Translation |
| title_short | Knowledge Graph Embedding by Dynamic Translation |
| title_sort | knowledge graph embedding by dynamic translation |
| topic | Dynamic translation embeddings knowledge graph translation-based models |
| url | https://ieeexplore.ieee.org/document/8057770/ |
| work_keys_str_mv | AT liangchang knowledgegraphembeddingbydynamictranslation AT manlizhu knowledgegraphembeddingbydynamictranslation AT tianlonggu knowledgegraphembeddingbydynamictranslation AT chenzhongbin knowledgegraphembeddingbydynamictranslation AT junyanqian knowledgegraphembeddingbydynamictranslation AT jizhang knowledgegraphembeddingbydynamictranslation |