一种融入实体描述的自适应知识表示模型  

An Adaptive Model for Knowledge Representation With Entity Description

作　　者：翟社平 王书桓 尚定蓉 董苏苏 ZHAI Sheping;WANG Shuhuan;SHANG Dingrong;DONG Susu(School of Computer Science and Technology,Xi'an University of Posts and Telecommunications,Xi'an,Shaanxi 710121,China;Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing,Xi'an,Shaanxi 710121,China)

机构地区：[1]西安邮电大学计算机学院,陕西西安710121 [2]陕西省网络数据分析与智能处理重点实验室,陕西西安710121

出　　处：《中文信息学报》2021年第1期43-53,共11页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61373116);工业和信息化部通信软科学项目(2018R26);西安邮电大学研究生创新基金项目(CXJJLY2018067);西安邮电大学大学生科技立项(2020-B-015);国家级大学生创新创业训练计划(S202011664003)。

摘　　要：知识表示学习旨在在连续的低维向量空间中表示知识图谱的实体和关系,但是现有的表示模型大多仅利用三元组的结构信息,而忽略了具有丰富语义的实体描述信息。为此,该文提出了一种基于实体描述的联合表示模型(joint representation based on entity descriptions,JRED)。具体来说,模型引入位置向量和注意力机制设计了AttentionBi-LSTM文本编码器,可以根据不同的关系从文本描述中动态选择最相关的信息。同时,采用一种自适应表示方法,为每个特征维度区别地赋予权重,并以此方法为基础通过门控机制共同学习文本和结构的联合表示。该文在链接预测和三元组分类任务上评估该模型,实验结果表明,模型在各项指标上均取得了很大的提升,尤其在Mean Rank指标上有明显优势。Knowledge representation learning aims to represent the entities and relations of a knowledge graphs in a continuous low-dimensional vector space. However, most of the existing models only use the structure information of triples and ignore the entity descriptions with rich semantic information. This paper proposes a joint representation based on entity descriptions(JRED). Specifically, this model introduces position vector and attention mechanism to design the Attention_Bi-LSTM encoder, which can dynamically select the most relevant information from the text descriptions according to different relations. At the same time, this paper adopts an adaptive representation method, which assigns different weights to every feature dimension. Based on this method, this model learns the joint representation of text and structure through the gate mechanism. The model is evaluated on the tasks of both link prediction and triple classification. Experimental results show that the model has made great progress in various indicators, especially under the Mean Rank indicator.

关 键 词：知识表示 实体描述 自适应表示 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]