基于表示学习的开放域中文知识推理

知识库通常以网络的形式被组织起来,网络中每个节点代表实体,而每条连边则代表实体间的关系。为了利用这种网状知识库中的知识,往往需要设计专门的、复杂度较高的图算法。然而这些算法并不能很好适用于知识推理,尤其是随着知识库的知识规模不断扩大,基于网状结构知识库的推理很难较好地满足实时计算的需求。该文使用基于TransE模型的知识表示学习进行知识推理,包括对实体关系三元组中关系指示词以及尾实体的推理,其中关系指示词推理的实验取得了较好的结果,且推理过程无需设计复杂的算法,仅涉及向量的简单运算。另外,该文对原始TransE模型的代价函数进行改进,以更好地适用于开放域中文知识库表示学习。

Open Domain Knowledge Reasoning for Chinese Based on Representation Learning

Knowledge bases are usually represented as networks with nodes for entities and edges for relations. To utilize knowledge bases, people have to design algorithms with high complexity, which are not suitable for knowledge reasoning, or especially for expanding knowledge bases. This paper uses TransE-based model to learn representation for knowledge reasoning, including the study on relation indication reasoning and tail entity reasoning. The experiments on relation indication reasoning get an excelletn result without designing complex algorithms: just some simple operations in vector space. Besides, we improve original loss function of TransE model to be more suitable for open domain Chinese knowledge bases in representation learning.