TransREF:一种改进的基于邻域信息的知识表示模型

TransREF:An improved knowledge representation model based on neighborhood information

近年来,知识表示学习在智能推荐、智能问答,以及智能检索方面发挥了关键性作用,受到了广泛关注。知识表示学习旨在借助实体与关系的低维嵌入,将语义信息向量化,通过数学公式进行知识的推理。在众多知识表示学习模型中,TransE由于评分函数参数较少、计算复杂度低、计算效率高,被认为是最有前途的模型。然而,TransE在处理除一对一以外的复杂关系时,存在一定的局限性。为了解决这个问题所带来的困扰,提高知识嵌入的质量,本文提出了一种改进的基于翻译模型的知识表示模型TransREF。首先,借助关系矩阵投影,实现对实体和关系的嵌入;其次在原有向量的基础上加入关系邻域,增强模型的学习能力。在模型被训练期间,对于语义相似度高的实体,通过概率法实现对头实体与尾实体的替换,进而生成的较高质量的负例三元组,并且在选择关系邻域节点时采用五点随机法。最后,选择英文词典WordNet的子集WN18和Freebase子集FB15K上进行相关链接预测实验,之后在3个公开数据集WN11、FB13、FB15K开展三元组分类的实验。结果表明,相较于TransE、TransH,TransREF在MeanRank、Hits@10,以及ACC指标上都有较好的性能改善,证明了TransREF的有效性。

In recent years,knowledge representation learning has played a crucial role in intelligent recommendation,intelligent question answering,and intelligent retrieval,and has received widespread attention.Knowledge representation learning aims to vectorize semantic information and infer knowledge through mathematical formulas by means of low-dimensional embedding of entities and relationships.Among many knowledge representation learning models,TransE is considered to be the most promising model due to its fewer scoring function parameters,low computational complexity and high computational efficiency.However,TransE has some limitations in dealing with complex relationships other than one-to-one.In order to solve this problem and improve the quality of knowledge embedding,this paper proposes an improved knowledge representation model TransREF based on translation model.Firstly,the embedding of entities and relations is realized by means of relation matrix projection.Secondly,on the basis of the original vector,the relational neighborhood is added to enhance the learning ability of the model.During the training of the model and for entities with high semantic similarity,the replacement of the head entity and the tail entity is realized by the probability method,and then the high-quality negative example triples are generated,and the five-point random method is used to select the relationship neighborhood nodes.Finally,the relevant link prediction experiment is carried out on the subset WN18of WordNet and the subset FB15Kof Freebase,and then the triplet classification experiment is carried out on the three public datasets WN11,FB13and FB15K.The results show that compared with TransE and TransH,TransREF has better performance improvement in MeanRank,Hits@10,and ACC indicators,which proves the effectiveness of TransREF.