Due to the incompleteness of knowledge graphs (KGs), zero-shot link prediction (ZSLP) which aims to predict unobserved relations in KGs has attracted recent interest from researchers. A common solution is to use textual features of relations (e.g., surface name or textual descriptions) as auxiliary information to bridge the gap between seen and unseen relations. Current approaches learn an embedding for each word token in the text. These methods lack robustness as they suffer from the out-of-vocabulary (OOV) problem. Meanwhile, models built on character n-grams have the capability of generating expressive representations for OOV words. Thus, in this paper, we propose a Hierarchical N-Gram framework for Zero-Shot Link Prediction (HNZSLP), which considers the dependencies among character n-grams of the relation surface name for ZSLP. Our approach works by first constructing a hierarchical n-gram graph on the surface name to model the organizational structure of n-grams that leads to the surface name. A GramTransformer, based on the Transformer is then presented to model the hierarchical n-gram graph to construct the relation embedding for ZSLP. Experimental results show the proposed HNZSLP achieved state-of-the-art performance on two ZSLP datasets.
翻译:由于知识图表(KGs)不完善,旨在预测KGs中未观察到的关系的零光链接预测(ZSLP)最近引起了研究人员的兴趣。一个共同的解决办法是使用关系文字特征(如表面名称或文本描述)作为辅助信息,以弥补所见关系和不可见关系之间的差距。当前方法在文本中学习了每个字符号的嵌入。这些方法缺乏强健性,因为它们受到体外词汇(OOOOV)问题的影响。同时,以字符 ngs为基础的模型有能力生成OOV字的表达式。因此,在本文件中,我们提议为Zero-Shot 链接预测(HNZSLP)建立一个高层次的N-Gram框架,该框架考虑到 ZSLP 关系表面名称的字符 ngram。我们的方法首先在表面名称上构建一个等级的 ngramgram 图形,用来模拟导致表面名称的Ngrowth-SLSL 的组织结构结构。基于Gram Trangal-SL-SL 的SLSL 和SLSLSL的两级模型,然后展示了SL的SL的SL-SL-SL-SL-Sleval-S-SL-SL-SL-SL-SL-SL-SL-SL-Slevational-SL-SL-S-Sal-SBsal-SL-SF-SL-saldaldaldaldaldaldaldaldaldaldaldaldaldaldal 的模型,然后展示了Saldaldal-Sal-Saldaldaldaldaldaldaldald 的模型。