Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of-knowledge-graph (OOKG) entities added frequently, and we need to efficiently represent these entities. Most existing Knowledge Graph Embedding (KGE) methods cannot represent OOKG entities without costly retraining on the whole KG. To enhance efficiency, we propose a simple and effective method that inductively represents OOKG entities by their optimal estimation under translational assumptions. Moreover, given pretrained embeddings of the in-knowledge-graph (IKG) entities, our method even needs no additional learning. Experimental results on two KGC tasks with OOKG entities show that our method outperforms the previous methods by a large margin with higher efficiency.
@inproceedings{dai-etal-2021-inductively, title = "Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions", author = "Dai, Damai and Zheng, Hua and Luo, Fuli and Yang, Pengcheng and Liu, Tianyu and Sui, Zhifang and Chang, Baobao", editor = "Rogers, Anna and Calixto, Iacer and Vuli{\'c}, Ivan and Saphra, Naomi and Kassner, Nora and Camburu, Oana-Maria and Bansal, Trapit and Shwartz, Vered", booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.repl4nlp-1.10/", doi = "10.18653/v1/2021.repl4nlp-1.10", pages = "83--89", abstract = "Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of-knowledge-graph (OOKG) entities added frequently, and we need to efficiently represent these entities. Most existing Knowledge Graph Embedding (KGE) methods cannot represent OOKG entities without costly retraining on the whole KG. To enhance efficiency, we propose a simple and effective method that inductively represents OOKG entities by their optimal estimation under translational assumptions. Moreover, given pretrained embeddings of the in-knowledge-graph (IKG) entities, our method even needs no additional learning. Experimental results on two KGC tasks with OOKG entities show that our method outperforms the previous methods by a large margin with higher efficiency."}
%0 Conference Proceedings%T Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions%A Dai, Damai%A Zheng, Hua%A Luo, Fuli%A Yang, Pengcheng%A Liu, Tianyu%A Sui, Zhifang%A Chang, Baobao%Y Rogers, Anna%Y Calixto, Iacer%Y Vulić, Ivan%Y Saphra, Naomi%Y Kassner, Nora%Y Camburu, Oana-Maria%Y Bansal, Trapit%Y Shwartz, Vered%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)%D 2021%8 August%I Association for Computational Linguistics%C Online%F dai-etal-2021-inductively%X Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of-knowledge-graph (OOKG) entities added frequently, and we need to efficiently represent these entities. Most existing Knowledge Graph Embedding (KGE) methods cannot represent OOKG entities without costly retraining on the whole KG. To enhance efficiency, we propose a simple and effective method that inductively represents OOKG entities by their optimal estimation under translational assumptions. Moreover, given pretrained embeddings of the in-knowledge-graph (IKG) entities, our method even needs no additional learning. Experimental results on two KGC tasks with OOKG entities show that our method outperforms the previous methods by a large margin with higher efficiency.%R 10.18653/v1/2021.repl4nlp-1.10%U https://aclanthology.org/2021.repl4nlp-1.10/%U https://doi.org/10.18653/v1/2021.repl4nlp-1.10%P 83-89
[Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions](https://aclanthology.org/2021.repl4nlp-1.10/) (Dai et al., RepL4NLP 2021)