Knowledge Bases Completion Based on Multi-hop Paths

doi:10.13209/j.0479-8023.2021.103

Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2022, Vol. 58 ›› Issue (1): 7-12.DOI: 10.13209/j.0479-8023.2021.103

Previous Articles Next Articles

Knowledge Bases Completion Based on Multi-hop Paths

WANG Yinmiao, HAN Zhimin^†

Artificial Intelligence Institute, School of Automation, Hangzhou Dianzi University, Hangzhou 310018

Received:2021-06-08 Revised:2021-08-13 Online:2022-01-20 Published:2022-01-20
Contact: HAN Zhimin, E-mail: hanzm(at)hdu.edu.cn

基于多跳路径的知识库补全

王引苗, 韩志敏^†

杭州电子科技大学自动化学院人工智能研究所, 杭州 310018

通讯作者: 韩志敏, E-mail: hanzm(at)hdu.edu.cn
基金资助:
国家重点研发计划(2018AAA0101601)资助

Abstract

Abstract:

In order to complement knowledge bases (KBs), the authors propose a new path-based reasoning method, which uses the attention mechanism to combine entities and their types to represent the entities in the path and use the attention mechanism to summarize the absolute value of the difference between the relationship vector predicted by each path and the representation vector of the given relationship to calculate the confidence of the model. The results of experiment on benchmark data sets WN18RR and FB15k-237 show that the proposed model has better performance than the existing path-based relational reasoning methods.

Key words: knowledge bases (KBs) completion, path-based reasoning, attention mechanism

摘要：

为了对知识库(KBs)进行补全, 提出一种新的基于路径的推理方法, 使用注意力机制, 将实体与其类型相结合, 共同对路径中的实体进行表示, 并使用注意力机制对每条路径预测的关系向量与给定关系的表示向量之差的绝对值进行汇总来计算模型的置信度。在基准数据集WN18RR和FB15k-237上的实验结果表明, 与现有的基于路径的关系推理方法相比, 所提方法具有更好的性能。

关键词: 知识库(KBs)补全, 基于路径的推理, 注意力机制

WANG Yinmiao, HAN Zhimin. Knowledge Bases Completion Based on Multi-hop Paths[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(1): 7-12.

王引苗, 韩志敏. 基于多跳路径的知识库补全[J]. 北京大学学报自然科学版, 2022, 58(1): 7-12.

Add to citation manager EndNote|Ris|BibTeX

URL: https://xbna.pku.edu.cn/EN/10.13209/j.0479-8023.2021.103

https://xbna.pku.edu.cn/EN/Y2022/V58/I1/7

[1]	DING Na, LIU Peng, SHAO Huipeng, WANG Xuekui. Bi-Attention Text-Keyword Matching for Law Recommendation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(1): 79-88.
[2]	WANG Rui, LIANG Jianguo, HUA Rong. Radiology Report Generation Method Based on Multi-scale Feature Parsing [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(1): 71-78.
[3]	LI Chao, HOU Xia, QIAO Xiuming. A Low-Resource Named Entity Recognition Method for Cultural Heritage Field Incorporating Knowledge Fusion [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(1): 13-22.
[4]	TIAN Yuan, PANG Xiao, ZHAO Wenyi, CHANG Xiaoyin, CHENG Chuyun, ZOU Pei, CAO Xiaocheng. A Transformer-Based Model for Short-Term Landslide Displacement Prediction [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(2): 197-210.
[5]	GAO Xiaoqian, ZHOU Xiabing, ZHANG Min. A Multi-information Perception Based Method for Question Answering in Multi-party Conversation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(1): 21-29.
[6]	SU Fenglong, SUN Chengzhe, JING Ning. A Context-Fusion Method for Entity Extraction Based on Residual Gated Convolution Neural Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(1): 69-76.
[7]	WAN Zhang, ZHANG Yujie, LIU Mingtong, XU Jin’an, CHEN Yufeng. Object Space Relation Mechanism Fused Image Caption Method [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2021, 57(1): 75-82.
[8]	WU Ruiying, KONG Fang. Event Coreference Resolution with Document Representation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(1): 82-88.
[9]	JIA Yunlong, HAN Donghong, LIN Haiyuan, WANG Guoren, XIA Li. Consumption Intent Recognition Algorithms for Weibo Users [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(1): 68-74.
[10]	LIU Mingtong, ZHANG Yujie, ZHANG Shu, MENG Yao, XU Jin’an, CHEN Yufeng. A Multi-Mechanism Fused Paraphrase Generation Model with Joint Auto-Encoding Learning [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(1): 53-60.
[11]	HUANG Yan, SUN Haili, XU Ke, YU Xiaoyang, WANG Tongyang, ZHANG Xinfang, LU Songfeng. Discourse-Level Text Generation Method Based on Topical Constraint [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(1): 9-15.
[12]	LI Lanjun, ZHOU Junsheng, GU Yanhui, Qü Weiguang. Similar Legal Case Retrieval Based on Improved Siamese Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(1): 84-90.
[13]	ZHANG Qinglin, DU Jiachen, XU Ruifeng. Sarcasm Detection Based on Adversarial Learning [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(1): 29-36.
[14]	ZHOU Botong, SUN Chengjie, LIN Lei, LIU Bingquan. LSTM Based Question Answering for Large Scale Knowledge Base [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 286-292.

Knowledge Bases Completion Based on Multi-hop Paths

基于多跳路径的知识库补全

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 14

Recommended Articles

Metrics