An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding
Knowledge bases such as Freebase, YAGO, DBPedia, and Nell contain a number of facts with various entities and relations. Since they store many facts, they are regarded as core resources for many natural language processing tasks. Nevertheless, they are not normally complete and have many missing fac...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/8/2651 |
| _version_ | 1797570805613199360 |
|---|---|
| author | Su Jeong Choi Hyun-Je Song Seong-Bae Park |
| author_facet | Su Jeong Choi Hyun-Je Song Seong-Bae Park |
| author_sort | Su Jeong Choi |
| collection | DOAJ |
| description | Knowledge bases such as Freebase, YAGO, DBPedia, and Nell contain a number of facts with various entities and relations. Since they store many facts, they are regarded as core resources for many natural language processing tasks. Nevertheless, they are not normally complete and have many missing facts. Such missing facts keep them from being used in diverse applications in spite of their usefulness. Therefore, it is significant to complete knowledge bases. Knowledge graph embedding is one of the promising approaches to completing a knowledge base and thus many variants of knowledge graph embedding have been proposed. It maps all entities and relations in knowledge base onto a low dimensional vector space. Then, candidate facts that are plausible in the space are determined as missing facts. However, any single knowledge graph embedding is insufficient to complete a knowledge base. As a solution to this problem, this paper defines knowledge base completion as a ranking task and proposes a committee-based knowledge graph embedding model for improving the performance of knowledge base completion. Since each knowledge graph embedding has its own idiosyncrasy, we make up a committee of various knowledge graph embeddings to reflect various perspectives. After ranking all candidate facts according to their plausibility computed by the committee, the top-<i>k</i> facts are chosen as missing facts. Our experimental results on two data sets show that the proposed model achieves higher performance than any single knowledge graph embedding and shows robust performances regardless of <i>k</i>. These results prove that the proposed model considers various perspectives in measuring the plausibility of candidate facts. |
| first_indexed | 2024-03-10T20:30:37Z |
| format | Article |
| id | doaj.art-0c5762f944f44051a752894f106bf9cb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T20:30:37Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0c5762f944f44051a752894f106bf9cb2023-11-19T21:22:18ZengMDPI AGApplied Sciences2076-34172020-04-01108265110.3390/app10082651An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph EmbeddingSu Jeong Choi0Hyun-Je Song1Seong-Bae Park2Institute of Convergence Technology, KT, 151 Taebong-ro, Seocho-gu, Seoul 06763, KoreaDepartment of Information Technology, Jeonbuk National University, 567 Baekje-daero, Deokjin-gu, Jeonju-si 54896, Jeollabuk-do, KoreaDepartment of Computer Science and Engineering, Kyung Hee University, 1732 Deogyeong-daero, Yongin-si 17104, Gyeonggi-do, KoreaKnowledge bases such as Freebase, YAGO, DBPedia, and Nell contain a number of facts with various entities and relations. Since they store many facts, they are regarded as core resources for many natural language processing tasks. Nevertheless, they are not normally complete and have many missing facts. Such missing facts keep them from being used in diverse applications in spite of their usefulness. Therefore, it is significant to complete knowledge bases. Knowledge graph embedding is one of the promising approaches to completing a knowledge base and thus many variants of knowledge graph embedding have been proposed. It maps all entities and relations in knowledge base onto a low dimensional vector space. Then, candidate facts that are plausible in the space are determined as missing facts. However, any single knowledge graph embedding is insufficient to complete a knowledge base. As a solution to this problem, this paper defines knowledge base completion as a ranking task and proposes a committee-based knowledge graph embedding model for improving the performance of knowledge base completion. Since each knowledge graph embedding has its own idiosyncrasy, we make up a committee of various knowledge graph embeddings to reflect various perspectives. After ranking all candidate facts according to their plausibility computed by the committee, the top-<i>k</i> facts are chosen as missing facts. Our experimental results on two data sets show that the proposed model achieves higher performance than any single knowledge graph embedding and shows robust performances regardless of <i>k</i>. These results prove that the proposed model considers various perspectives in measuring the plausibility of candidate facts.https://www.mdpi.com/2076-3417/10/8/2651knowledge base completionknowledge graph constructionknowledge graph embeddingcommittee machine |
| spellingShingle | Su Jeong Choi Hyun-Je Song Seong-Bae Park An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding Applied Sciences knowledge base completion knowledge graph construction knowledge graph embedding committee machine |
| title | An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding |
| title_full | An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding |
| title_fullStr | An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding |
| title_full_unstemmed | An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding |
| title_short | An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding |
| title_sort | approach to knowledge base completion by a committee based knowledge graph embedding |
| topic | knowledge base completion knowledge graph construction knowledge graph embedding committee machine |
| url | https://www.mdpi.com/2076-3417/10/8/2651 |
| work_keys_str_mv | AT sujeongchoi anapproachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding AT hyunjesong anapproachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding AT seongbaepark anapproachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding AT sujeongchoi approachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding AT hyunjesong approachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding AT seongbaepark approachtoknowledgebasecompletionbyacommitteebasedknowledgegraphembedding |