@inproceedings{qiu-etal-2024-joint,
    title = "Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion",
    author = "Qiu, Chenyu  and
      Qian, Pengjiang  and
      Wang, Chuang  and
      Yao, Jian  and
      Liu, Li  and
      Fang, Wei  and
      Ng, Eddie-Yin-Kwee",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2024.emnlp-main.851/",
    doi = "10.18653/v1/2024.emnlp-main.851",
    pages = "15257--15269",
    abstract = "Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model{'}s prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4{\%} and Hits@1+6.4{\%}) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60{\%}."
}