[1]LI Junhuai,WU Yunwen,WANG Huaijun,et al.Knowledge graph representation learning model combining entity description and path information[J].CAAI Transactions on Intelligent Systems,2023,18(1):153-161.[doi:10.11992/tis.202112010]
Copy

Knowledge graph representation learning model combining entity description and path information

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 18 Number of periods: 2023 1 Page number: 153-161 Column: 人工智能院长论坛 Public date: 2023-01-05
Title:
Knowledge graph representation learning model combining entity description and path information
Author(s):
LI Junhuai1; 2;  WU Yunwen1; 2;  WANG Huaijun1; 2;  LI Zhichao1; 2;  XU Jiang3
1. Collaborative Innovation Center of Modern Equipment Green Manufacturing in Shaanxi Province, Xi’an University of Technology, Xi’an 710048, China;
2. School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China;
3. China National Heavy Machinery Research Institute Co., Ltd., Xi’an 710032, China
Keywords:
knowledge graph; expression learning; multidimensional vector; multi-hop reasoning ability; entity description; path information; energy function; vector fusion
CLC:
TP301.6
DOI:
10.11992/tis.202112010
Abstract:
Knowledge graph representation learning is a process of representing knowledge graph entities and relations in a multidimensional vector through specific rules. Existing representation learning methods are mostly used to solve the single-hop knowledge graph question-and-answer task, but their multi-hop reasoning ability cannot meet the actual demand. To improve the multi-hop reasoning ability, a knowledge graph representation learning model combining entity description and path information is proposed. First, the learning vector of entity and relation representation is obtained using the pre-training language model RoBERTa. Second, OPTransE is used to transform the knowledge graph into a vector integrating the path information of an ordered relation. Finally, the total energy function is constructed to fuse the vectors of entity description and path information. The feasibility and validity of the model are verified by comparing its performance in a link prediction task with that of the mainstream knowledge graph representation learning model.
References:
[1] XIE Ruobing, LIU Zhiyuan, JIA Jia, et al. Representation learning of knowledge graphs with entity descriptions[J]. Proceedings of the AAAI conference on artificial intelligence, 2016, 30(1): 2659–2665.
[2] 刘知远, 孙茂松, 林衍凯, 等. 知识表示学习研究进展[J]. 计算机研究与发展, 2016, 53(2): 247–261
LIU Zhiyuan, SUN Maosong, LIN Yankai, et al. Knowledge representation learning: a review[J]. Journal of computer research and development, 2016, 53(2): 247–261
[3] 李涛, 王次臣, 李华康. 知识图谱的发展与构建[J]. 南京理工大学学报, 2017, 41(1): 22–34
LI Tao, WANG Cichen, LI Huakang. Development and construction of knowledge graph[J]. Journal of Nanjing University of Science and Technology, 2017, 41(1): 22–34
[4] 张正航, 钱育蓉, 行艳妮, 等. 基于TransE的表示学习方法研究综述[J]. 计算机应用研究, 2021, 38(3): 656–663
ZHANG Zhenghang, QIAN Yurong, XING Yanni, et al. Survey of representation learning methods based on TransE[J]. Application research of computers, 2021, 38(3): 656–663
[5] LIN Yankai, LIU Zhiyuan, LUAN Huanbo, et al. Modeling relation paths for representation learning of knowledge bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Lisbon, Portugal. Stroudsburg: Association for Computational Linguistics, 2015: 705?714.
[6] YANG Bishan, YIH W T, HE Xiaodong, et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL]. (2014?12?20) [2021?12?01].https://arxiv.org/abs/1412.6575.
[7] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//ICML’16: Proceedings of the 33rd International Conference on International Conference on Machine Learning-Volume 48. New York: ACM, 2016: 2071?2080.
[8] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New Orleans: AAAI Press, 2018, 32(1): 1811?1818.
[9] NGUYEN D Q, NGUYEN T D, NGUYEN D Q, et al. A novel embedding model for knowledge base completion based on convolutional neural network[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). New Orleans: Association for Computational Linguistics, 2018: 327?333.
[10] 王智悦, 于清, 王楠, 等. 基于知识图谱的智能问答研究综述[J]. 计算机工程与应用, 2020, 56(23): 1–11
WANG Zhiyue, YU Qing, WANG Nan, et al. Survey of intelligent question answering research based on knowledge graph[J]. Computer engineering and applications, 2020, 56(23): 1–11
[11] LIU Yinhan, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach[EB/OL]. (2019?7?26)[2021?12?01].https://arxiv.org/abs/1907.11692.
[12] ZHU Yao, LIU Hongzhi, WU Zhonghai, et al. Representation learning with ordered relation paths for knowledge graph completion[EB/OL]. (2019?09?26) [2021?12?01].https://arxiv.org/abs/1909.11864.
[13] 缴霖境, 闫威. 融合实体概念描述与图像特征的知识图谱表示学习研究[J]. 计算机应用研究, 2021, 38(6): 1759–1764
JIAO Linjing, YAN Wei. Research on knowledge graph representation learning combining entity concept description and image features[J]. Application research of computers, 2021, 38(6): 1759–1764
[14] XIE Ruobing, LIU Zhiyuan, SUN Maosong. Representation learning of knowledge graphs with hierarchical types[C]//IJCAI’16: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. New York: ACM, 2016: 2965?2971.
[15] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[M]//The Semantic Web. Cham: Springer International Publishing, 2018: 593?607.
[16] BORDES A, USUNIER N, GARCIA-DURáN A, et al. Translating embeddings for modeling multi-relational data[C]//NIPS’13: Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2. New York: ACM, 2013: 2787?2795.
[17] CAI Liwei, WANG W Y. KBGAN: adversarial learning for knowledge graph embeddings[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans: Association for Computational Linguistics, 2018: 1470?1480.
[18] SUN Zhiqing, DENG Zhihong, NIE Jianyun, et al. RotatE: knowledge graph embedding by relational rotation in complex space[EB/OL]. (2018?09?27)[2021?12?01].https://www.semanticscholar.org/paper/RotatE%3A-Knowledge-Graph-Embedding-by-Relational-in-Sun-Deng/8f096071a09701012c9c279aee2a88143a295935.
[19] JIANG Xiaotian, WANG Quan, WANG Bin. Adaptive convolution for multi-relational learning[C]//Proceedings of the 2019 Conference of the North. Minneapolis: Association for Computational Linguistics, 2019: 978?987.
[20] BALAZEVIC I, ALLEN C, HOSPEDALES T. TuckER: tensor factorization for knowledge graphcompletion[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019: 5184?5193.
[21] ZHANG Zhanqiu, CAI Jianyu, ZHANG Yongdong, et al. Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI Press, 2020, 34(3): 3065?3072.
[22] VASHISHTH S, SANYAL S, NITIN V, et al. InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI Press, 2020, 34(3): 3009?3016.
[23] YE Rui, LI Xin, FANG Yujie, et al. A vectorized relational graph convolutional network for multi-relational network alignment[EB/OL]. (2019?08?01)[2021?12?01].https://www.semanticscholar.org/paper/A-Vectorized-Relational-Graph-Convolutional-Network-Ye-Li/d6adbd838cb69d3694659bde7c1bf464a8438caf.
[24] KAZEMI S M, POOLE D. SimplE embedding for link prediction in knowledge graphs[EB/OL]. (2018?02?13)[2021?12?01].https://www.semanticscholar.org/paper/SimplE-Embedding-for-Link-Prediction-in-Knowledge-Kazemi-Poole/70af3ee98c53441d9090119f7b76efb1b6d03edd.
[25] NIU Guanglin, ZHANG Yongfei, LI Bo, et al. Rule-guided compositional representation learning on knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI Press, 2020, 34(3): 2950?2958.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems