Influence of Embeddings Construction Methods on Entity Alignment Approaches
https://doi.org/10.25205/1818-7900-2022-20-2-5-17
Abstract
The problem of merging knowledge graphs (KG) presented in different languages is becoming more and more relevant. The main stage for its solution is the identification of equivalent entities and their descriptions. It is also known as the entity alignment problem. The recent research shows that existing approaches are not effective for all languages. This article presents the experiments aimed at improving the alignment of entities on an English-Russian dataset. The results obtained are considered from the point of view both of the whole graph and of individual types of entities. The influence of the number of relations and attributes on the accuracy of the algorithms is estimated.
About the Authors
D. I. Gusev
Novosibirsk State University
Russian Federation
Russian Federation
Daniil I. Gusev, master’s student
Novosibirsk
Z. V. Apanovich
Novosibirsk State University;
A.P. Ershov Institute of Informatics Systems of the Siberian Branch of the Russian Academy of Sciences
Russian Federation
Russian Federation
Zinaida V. Apanovich, senior researcher
Novosibirsk
References
1. Bordes A., Usunier N., Garcia-Durán A., Weston J., Yakhnenko O. Translating embeddings for modeling multi-relational data. Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013, vol. 2, p. 2787–2795. DOI 10.5555/2999792.2999923.
2. Chen M., Tian Y., Chang K., Skiena S., Zaniolo C. Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment. Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018, p. 3998–4004. DOI 10.24963/ijcai.2018/556.
3. Xu K., Wang L., Yu M., Feng Y., Song Y., Wang Z., Yu D. Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, p. 3156–3161. DOI 10.18653/v1/P19-1304.
4. Rossi A., Barbosa D., Firmani D., Matinata A., Merialdo P. Knowledge Graph Embedding for Link Prediction: A Comparative Analysis. ACM Transactions on Knowledge Discovery from Data, 2021, vol. 15, p. 1–49. DOI 10.1145/3424672.
5. Sun Z., Zhang Q., Hu W., Wang C., Chen M., Akrami F., Li C. A benchmarking study of embedding-based entity alignment for knowledge graphs. Proceedings of the VLDB Endowment, 2020, vol. 13, p. 2326–2340. DOI 10.14778/3407790.3407828.
6. Gnezdilova V. A., Apanovich, Z. V. Russian-English dataset and comparative analysis of algorithms for cross-language embeddingbased entity alignment. Journal of Physics: Conference Series, 2021, vol. 2099. DOI 10.1088/1742-6596/2099/1/012023.
7. Zhang Q., Sun Z., Hu W., Chen M., Guo L., Qu Y. Multi-view Knowledge Graph Embedding for Entity Alignment. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, p. 5429–5435. DOI 10.24963/ijcai.2019/754.
8. Wu Y., Liu X., Feng Y., Wang Z., Yan R., Zhao D. Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, p. 5278–5284. DOI 10.24963/ijcai.2019/733.
9. Mao X., Wang W., Wu Y., Lan M. From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, p. 2843–2853. DOI 10.18653/v1/2021.emnlp-main.226.
10. Guo L., Sun Z., Hu W. Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs. Proceedings of the 36th International Conference on Machine Learning, 2019, vol. 57, p. 2505–2514.
11. Yang Z., Dai Z., Yang Y., Carbonell J., Salakhutdinov R., Le Q. XLNet: Generalized Autoregressive Pretraining for Language Understanding. Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019, p. 5753–5763. DOI 10.5555/3454287.3454804.
12. Feng F., Yang Y., Cer D., Arivazhagan N., Wang W. Language-agnostic BERT Sentence Embedding. ArXiv, 2020. DOI 10.48550/arXiv.2007.01852.
Review
For citations:
Gusev D.I., Apanovich Z.V. Influence of Embeddings Construction Methods on Entity Alignment Approaches. Vestnik NSU. Series: Information Technologies. 2022;20(2):5-17. (In Russ.) https://doi.org/10.25205/1818-7900-2022-20-2-5-17
Views:
173
Email this article 