Embodying the Number of an Entity’s Relations for Knowledge Representation Learning
Abstract
Knowledge representation learning (knowledge graph embedding) plays a critical role in the application of knowledge graph construction. The multi-source information knowledge representation learning, which is one class of the most promising knowledge representation learning at present, mainly focuses on learning a large number of useful additional information of entities and relations in the knowledge graph into their embeddings, such as the text description information, entity type information, visual information, graph structure information, etc. However, there is a kind of simple but very common information — the number of an entity’s relations which means the number of an entity’s semantic types has been ignored. This work proposes a multi-source knowledge representation learning model KRL-NER, which embodies information of the number of an entity’s relations between entities into the entities’ embeddings through the attention mechanism. Specifically, first of all, we design and construct a submodel of the KRL-NER LearnNER which learns an embedding including the information on the number of an entity’s relations; then, we obtain a new embedding by exerting attention onto the embedding learned by the models such as TransE with this embedding; finally, we translate based onto the new embedding. Experiments, such as related tasks on knowledge graph: entity prediction, entity prediction under different relation types, and triple classification, are carried out to verify our model. The results show that our model is effective on the large-scale knowledge graphs, e.g. FB15K.
References
- 1. , Introducing the knowledge graph: Things, not strings, Official Google Blog (2012). Google Scholar
- 2. , A survey on knowledge graphs: Representation, acquisition, and applications, IEEE Trans. Neural Netw. Learn. Syst. (2021) 1–21, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9416312. ISI, Google Scholar
- 3. , A review: Knowledge reasoning over knowledge graph, Expert Syst. Appl. 141 (2020) 112948.1–112948.21. Crossref, ISI, Google Scholar
- 4. , Applications of knowledge representation learning, MDATA: A New Knowledge Representation Model: Theory, Methods and Applications (2021), pp. 165–184. Crossref, Google Scholar
- 5. , A survey on approaches and applications of knowledge representation learning, in IEEE 5th Int. Conf. on Data Science in Cyberspace, 2020, pp. 312–319. Crossref, Google Scholar
- 6. Y. Lin, X. Han, R. Xie, Z. Liu and M. Sun, Knowledge representation learning: A quantitative review, arXiv:1812.10901. Google Scholar
- 7. , Knowledge graph fusion for smart systems: A survey, Inform. Fusion 61 (2020) 56–70. Crossref, ISI, Google Scholar
- 8. , Improved entity linking for simple question answering over knowledge graph, Int. J. Softw. Eng. Knowl. Eng. 31 (2021) 55–80. Link, ISI, Google Scholar
- 9. , Knowledge graph embedding: A survey of approaches and applications, IEEE Trans. Knowl. Data Eng. 29 (2017) 2724–2743. Crossref, ISI, Google Scholar
- 10. , Knowledge graph embedding for link prediction: A comparative analysis, ACM Trans. Knowl. Discov. Data 15(2) (2021) 1–49. Crossref, ISI, Google Scholar
- 11. , Translating embeddings for modeling multi-relational data, Adv. Neural Inform. Process. Syst. 26 (2013) 2787–2795. Google Scholar
- 12. , Analogical inference for multi-relational embeddings, in Int. Conf. Machine Learning, 2017, pp. 2168–2178. Google Scholar
- 13. B. Yang, W.-T. Yih, X. He, J. Gao and L. Deng, Embedding entities and relations for learning and inference in knowledge bases, arXiv:1412.6575. Google Scholar
- 14. Q. Liu, H. Jiang, A. Evdokimov, Z.-H. Ling, X. Zhu, S. Wei and Y. Hu, Probabilistic reasoning via deep learning: Neural association models, arXiv:1603.07704. Google Scholar
- 15. I. Balazević, C. Allen and T. M. Hospedales, Tucker: Tensor factorization for knowledge graph completion, arXiv:1901.09590. Google Scholar
- 16. , Knowledge graph embedding by translating on hyperplanes, in Proc. AAAI Conf. Artificial Intelligence, Vol. 28, 2014. Crossref, Google Scholar
- 17. , Transition-based knowledge graph embedding with relational mapping properties, in Proc. 28th Pacific Asia Conf. Language, Information and Computation, 2014, pp. 328–337. Google Scholar
- 18. , Learning entity and relation embeddings for knowledge graph completion, in Proc. AAAI Conf. Artificial Intelligence, 2015. Crossref, Google Scholar
- 19. G. Ji, S. He, L. Xu, K. Liu and J. Zhao, Knowledge graph embedding via dynamic mapping matrix, in Proc. 53rd Annual Meeting of the Association for Computational Linguistics and 7th Int. Joint Conf. Natural Language Processing, Vol. 1, 2015, pp. 687–696. Google Scholar
- 20. , Rotate: Knowledge graph embedding by relational rotation in complex space, Int. Conf. Learning Representations, 2019. Google Scholar
- 21. , Learning knowledge graph embedding with heterogeneous relation attention networks, IEEE Trans. Neural Netw. Learn. Syst. (2021) 1–13, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9359364. ISI, Google Scholar
- 22. , Learning to exploit long-term relational dependencies in knowledge graphs, Int. Conf. Machine Learning, 2019, pp. 2505–2514. Google Scholar
- 23. , A capsule network-based embedding model for knowledge graph completion and search personalization, in Proc. Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, 2019, pp. 2180–2189. Crossref, Google Scholar
- 24. , Text-enhanced representation learning for knowledge graph, in Proc. Int. Joint Conf. Artificial Intelligent, 2016, pp. 4–17. Google Scholar
- 25. , Representation learning of knowledge graphs with entity descriptions, in Proc. AAAI Conf. Artificial Intelligence, Vol. 30, 2016. Crossref, Google Scholar
- 26. , Ssp: Semantic space projection for knowledge graph embedding with text descriptions, in Proc. AAAI Conf. Artificial Intelligence, 2017, pp. 3104–3110. Crossref, Google Scholar
- 27. , Knowledge graph embedding with concepts, Knowl. Based Syst. 164 (2019) 38–44. Crossref, ISI, Google Scholar
- 28. , Structure-augmented text representation learning for efficient knowledge graph completion, in Proc. Web Conf., 2021, pp. 1737–1748. Crossref, Google Scholar
- 29. , Representation learning of knowledge graphs with hierarchical types, in Proc. Int. Joint Conf. Artificial Intelligent, 2016, pp. 2965–2971. Google Scholar
- 30. G. Niu, B. Li, Y. Zhang, S. Pu and J. Li, Autoeter: Automated entity type representation for knowledge graph embedding, arXiv:2009.12030. Google Scholar
- 31. , Translating embeddings for knowledge graph completion with relation attention mechanism, in Proc. Int. Joint Conf. Artificial Intelligent, 2018, pp. 4286–4292. Crossref, Google Scholar
- 32. , Integrating image-based and knowledge-based representation learning, IEEE Trans. Cognit. Develop. Syst. 12 (2020) 169–178. Crossref, ISI, Google Scholar
- 33. S. Y. Min, P. Raghavan and P. Szolovits, TransINT: Embedding implication rules in knowledge graphs with isomorphic intersections of linear subspaces, arXiv:2007.00271. Google Scholar
- 34. , ChronoR: Rotation based temporal knowledge graph embedding, in Proc. AAAI Conf. Artificial Intelligence, 2021. Crossref, Google Scholar
- 35. , Representation learning with ordered relation paths for knowledge graph completion, in Conf. Empirical Methods in Natural Language Processing and 9th Int. Joint Conf. on Natural Language Processing, 2020, pp. 2662–2671. Google Scholar
- 36. , Enhancing knowledge graph embedding by composite neighbors for link prediction, Computing 102(12) (2020) 2587–2606. Crossref, ISI, Google Scholar
- 37. , A semi-supervised model for knowledge graph embedding, Data Mining Knowl. Discov. 34(1) (2020) 1–20. Crossref, ISI, Google Scholar
- 38. S. Chaudhari, G. Polatkan, R. Ramanath and V. Mithal, An attentive survey of attention models, arXiv:1904.02874. Google Scholar
- 39. ,
Attention is all you need , in Advances in Neural Information Processing Systems (Curran Associates, 2017), pp. 5998–6008. Google Scholar - 40. , Neural machine translation by jointly learning to align and translate, in 3rd Int. Conf. Learning Representations, 2015, pp. 1–15. Google Scholar
- 41. , Image-embodied knowledge representation learning, in Int. Joint Conf. Artificial Intelligence, 2017, pp. 3140–3146. Crossref, Google Scholar
- 42. , A neural probabilistic language model, J. Mach. Learn. Res. 3 (2003) 1137–1155. ISI, Google Scholar
- 43. , Efficient estimation of word representations in vector space, in 1st Int. Conf. Learning Representations, 2013. Google Scholar
- 44. , Word representations: A simple and general method for semi-supervised learning, in Proc. 48th Annual Meeting of the Association for Computational Linguistics, 2010, pp. 384–394. Google Scholar
- 45. , Distributed representations of words and phrases and their compositionality, Adv. Neural Inform. Process. Syst. 26 (2013) 3111–3119. Google Scholar
- 46. , Freebase: A collaboratively created graph database for structuring human knowledge, in Proc. ACM SIGMOD Int. Conf. Management of Data, 2008, pp. 1247–1250. Crossref, Google Scholar
- 47. , WordNet: A lexical database for english, Commun. ACM 38(11) (1995) 39–41. Crossref, ISI, Google Scholar
- 48. , OpenKE: An open toolkit for knowledge embedding, in Proc. Conf. Empirical Methods in Natural Language Processing: System Demonstrations, 2018, pp. 139–144. Crossref, Google Scholar
Remember to check out the Most Cited Articles! |
---|
Check out our titles in C++ Programming! |