当前位置: X-MOL 学术Inf. Process. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Cross-Media Deep Relationship Classification Method Using Discrimination Information
Information Processing & Management ( IF 7.4 ) Pub Date : 2020-07-13 , DOI: 10.1016/j.ipm.2020.102344
Weifeng Hu , Baosen Ma , Zeqiang Li , Yujun Li , Yue Wang

Relation classification is one of the most fundamental tasks in the area of cross-media, which is essential for many practical applications such as information extraction, question&answer system, and knowledge base construction. In the cross-media semantic retrieval task, in order to meet the needs of cross-media uniform representation and semantic analysis, it is necessary to analyze the semantic potential relationship and construct semantic-related cross-media knowledge graph. The relationship classification technology is an important part of solving semantic correlation classification. Most of existing methods regard relation classification as a multi-classification task, without considering the correlation between different relationships. However, two relationships in the opposite directions are usually not independent of each other. Hence, this kind of relationships are easily confused in the traditional way. In order to solve the problem of confusing the relationships of the same semantic with different entity directions, this paper proposes a neural network fusing discrimination information for relation classification. In the proposed model, discrimination information is used to distinguish the relationship of the same semantic with different entity directions, the direction of entity in space is transformed into the direction of vector in mathematics by the method of entity vector subtraction, and the result of entity vector subtraction is used as discrimination information. The model consists of three modules: sentence representation module, relation discrimination module and discrimination fusion module. Moreover, two fusion methods are used for feature fusion. One is a Cascade-based feature fusion method, and another is a feature fusion method based on convolution neural network. In addition, this paper uses the new function added by cross-entropy function and deformed Max-Margin function as the loss function of the model. The experimental results show that the proposed discriminant feature is effective in distinguishing confusing relationships, and the proposed loss function can improve the performance of the model to a certain extent. Finally, the proposed model achieves 84.8% of the F1 value without any additional features or NLP analysis tools. Hence, the proposed method has a promising prospect of being incorporated in various cross-media systems.



中文翻译:

利用歧视信息的跨媒体深度关系分类方法

关系分类是跨媒体领域中最基本的任务之一,对于许多实际应用(例如信息提取,问答系统和知识库构建)而言,这是必不可少的。在跨媒体语义检索任务中,为了满足跨媒体统一表示和语义分析的需要,有必要分析语义潜在关系并构造与语义相关的跨媒体知识图。关系分类技术是解决语义相关分类的重要组成部分。现有的大多数方法都将关系分类视为多分类任务,而不考虑不同关系之间的相关性。但是,相反方向上的两个关系通常不是彼此独立的。因此,这种关系很容易以传统方式混淆。为了解决将相同语义与不同实体方向混淆的问题,提出了一种融合鉴别信息的神经网络进行关系分类的方法。在该模型中,利用区分信息来区分相同语义与不同实体方向的关系,并通过实体矢量减法的方法将空间中实体的方向转换为数学中的矢量方向,并得到实体的结果。矢量减法被用作判别信息。该模型由三个模块组成:句子表示模块,关系判别模块和判别融合模块。此外,两种融合方法用于特征融合。一种是基于级联的特征融合方法,另一种是基于卷积神经网络的特征融合方法。此外,本文还使用了交叉熵函数和变形后的Max-Margin函数相加的新函数作为模型的损失函数。实验结果表明,所提出的判别特征在区分混淆关系方面是有效的,所提出的损失函数可以在一定程度上改善模型的性能。最后,该模型无需任何其他功能或NLP分析工具即可达到F1值的84.8%。因此,所提出的方法具有被结合到各种跨媒体系统中的有希望的前景。本文使用交叉熵函数和变形的Max-Margin函数相加的新函数作为模型的损失函数。实验结果表明,所提出的判别特征在区分混淆关系方面是有效的,所提出的损失函数可以在一定程度上改善模型的性能。最后,所提出的模型无需任何其他功能或NLP分析工具即可达到F1值的84.8%。因此,所提出的方法具有被并入各种跨媒体系统中的广阔前景。本文使用交叉熵函数和变形的Max-Margin函数相加的新函数作为模型的损失函数。实验结果表明,所提出的判别特征在区分混淆关系方面是有效的,所提出的损失函数可以在一定程度上改善模型的性能。最后,所提出的模型无需任何其他功能或NLP分析工具即可达到F1值的84.8%。因此,所提出的方法具有被结合到各种跨媒体系统中的有希望的前景。提出的损失函数可以在一定程度上改善模型的性能。最后,所提出的模型无需任何其他功能或NLP分析工具即可达到F1值的84.8%。因此,所提出的方法具有被并入各种跨媒体系统中的广阔前景。提出的损失函数可以在一定程度上改善模型的性能。最后,所提出的模型无需任何其他功能或NLP分析工具即可达到F1值的84.8%。因此,所提出的方法具有被并入各种跨媒体系统中的广阔前景。

更新日期:2020-07-13
down
wechat
bug