| Li Shaojie(李少杰)* **,Chen Shudong**,Ouyang Xiaoye**,Gong Lichen* **.[J].高技术通讯(英文),2021,27(1):43~52 |
|
| Joint learning based on multi-shaped filters for knowledge graph completion |
| |
| DOI：10.3772/j.issn.1006-6748.2021.01.006 |
| 中文关键词: |
| 英文关键词: knowledge graph embedding (KGE), knowledge graph completion (KGC), convolutional neural network (CNN), joint learning, multi-shaped filter |
| 基金项目: |
| Author Name | Affiliation | | Li Shaojie(李少杰)* ** | (*School of Microelectronics,University of Chinese Academy of Sciences, Beijing 100049, P.R.China)
(**Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, P.R.China) | | Chen Shudong** | (**Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, P.R.China) | | Ouyang Xiaoye** | (**Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, P.R.China) | | Gong Lichen* ** | (*School of Microelectronics,University of Chinese Academy of Sciences, Beijing 100049, P.R.China)
(**Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, P.R.China) |
|
| Hits: 1419 |
| Download times: 1135 |
| 中文摘要: |
| |
| 英文摘要: |
| To solve the problem of missing many valid triples in knowledge graphs (KGs), a novel model based on a convolutional neural network (CNN) called ConvKG is proposed, which employs a joint learning strategy for knowledge graph completion (KGC). Related research work has shown the superiority of convolutional neural networks (CNNs) in extracting semantic features of triple embeddings. However, these researches use only one single-shaped filter and fail to extract semantic features of different granularity. To solve this problem, ConvKG exploits multi-shaped filters to co-convolute on the triple embeddings, joint learning semantic features of different granularity. Different shaped filters cover different sizes on the triple embeddings and capture pairwise interactions of different granularity among triple elements. Experimental results confirm the strength of joint learning, and compared with state-of-the-art CNN-based KGC models, ConvKG achieves the better mean rank (MR) and Hits@10 metrics on dataset WN18RR, and the better MR on dataset FB15k-237. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
