Comparing Knowledge Graph Representation Models for Link Prediction

被引：0

作者：

Chuanming Y. ^{[1
]}

Zhengang Z. ^{[1
]}

Lingge K. ^{[1
]}

机构：

[1] School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan

来源：

Data Analysis and Knowledge Discovery | 2021年 / 5卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Deep Learning; Knowledge Graph; Link Prediction; Representation Learning;

D O I：

10.11925/infotech.2096-3467.2021.0491

中图分类号：

学科分类号：

摘要：

[Objective] This study systematically reviews the internal mechanism and influencing factors of knowledge graph representation models, aiming to investigate their impacts on specific tasks. [Methods] For the link prediction task, we compared the performance of translation-based and semantic matching-based knowledge graph representation models on FB15K, WN18, FB15K-237 and WN18RR datasets. [Results] With the Hits@1 indicator, the TuckER model generated the best value on WN18, FB15K-237 and WN18RR datasets (0.946 0, 0.263 3 and 0.443 0, respectively), while the ComplEx model yielded the highest value on FB15K dataset (0.731 4). [Limitations] We only compared the effects of knowledge graph representation model on the link prediction and knowledge base QA tasks. More research is needed to examine their performance on information retrieval, recommendation system and other tasks. [Conclusions] There are significant differences between the translation-based and the semantic matching-based knowledge graph representation models. The score function, negative sampling, and optimization method of the knowledge graph representation model, as well as the proportion of training data have significant impacts on the results of the link prediction. © 2021, Chinese Academy of Sciences. All rights reserved.

引用

页码：29 / 44

页数：15

共 45 条

[1] Bollacker K, Cook R, Tufts P., Freebase: A Shared Database of Structured General Human Knowledge, Proceedings of the 22nd AAAI Conference on Artificial Intelligence, pp. 1962-1963, (2007)
[2] Bizer C, Lehmann J, Kobilarov G, Et al., DBpedia- A Crystallization Point for the Web of Data, Journal of Web Semantics, 7, 3, pp. 154-165, (2009)
[3] Wikidata
[4] Suchanek F M, Kasneci G, Weikum G., YAGO: A Large Ontology from Wikipedia and WordNet, Journal of Web Semantics, 6, 3, pp. 203-217, (2008)
[5] Zhang Y Z, Liu K, He S Z, Et al., Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
[6] Yang B S, Mitchell T., Leveraging Knowledge Bases in LSTMs for Improving Machine Reading, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1436-1446, (2017)
[7] Almousa M, Benlamri R, Khoury R., A Novel Word Sense Disambiguation Approach Using WordNet Knowledge Graph [OL]
[8] Ruan Xiaoyun, Liao Jianbin, Li Xiang, Et al., Interpretable Recommendation of Reinforcement Learning Based on Talent Knowledge Graph Reasoning, Data Analysis and Knowledge Discovery, 5, 6, pp. 36-50, (2021)
[9] Bellman R E., Dynamic Programming, (2003)
[10] Liu Zhiyuan, Sun Maosong, Lin Yankai, Et al., Knowledge Representation Learning: A Review, Journal of Computer Research and Development, 53, 2, pp. 247-261, (2016)

← 1 2 3 4 5 →