SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
复制标题
DOI：
10.1609/aaai.v31i1.10952
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
Han Xiao;Minlie Huang;Lian Meng;Xiaoyan Zhu
中科院分区：
文献类型：
--
作者：
Han Xiao;Minlie Huang;Lian Meng;Xiaoyan Zhu
知识图嵌入将知识图中的实体和关系表示为低维的连续向量，从而使知识图与机器学习模型兼容。虽然知识图嵌入的模型多种多样，但大多数方法只关注事实三元组，没有充分利用实体和关系的补充文本描述。为此，本文提出了符号三元组和文本描述共同学习的语义空间投影（SSP）模型。我们的模型建立了两个信息源之间的交互，并使用文本描述来发现语义关联并提供精确的语义嵌入。大量的实验表明，我们的方法在知识图完成和实体分类任务上取得了相对基线的实质性改进。
Knowledge graph embedding represents entities and relations in knowledge graph as low-dimensional, continuous vectors, and thus enables knowledge graph compatible with machine learning models. Though there have been a variety of models for knowledge graph embedding, most methods merely concentrate on the fact triples, while supplementary textual descriptions of entities and relations have not been fully employed. To this end, this paper proposes the semantic space projection (SSP) model which jointly learns from the symbolic triples and textual descriptions. Our model builds interaction between the two information sources, and employs textual descriptions to discover semantic relevance and offer precise semantic embedding. Extensive experiments show that our method achieves substantial improvements against baselines on the tasks of knowledge graph completion and entity classification.