arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1810.05320cs.CL
收藏

知识图谱中重要属性的识别

Important Attribute Identification in Knowledge Graph

Alibaba Group(阿里巴巴集团)

Shengjie Sun, Dong Yang, Hongchun Zhang, Yanxu Chen, Chao Wei, Xiaonan Meng, Yi Hu

摘要:

知识图谱(KG)由实体及其描述、属性以及实体之间的关系组成,在各种自然语言处理任务中得到越来越多的应用。在像Wikidata这样的典型知识图谱中,实体通常有大量的属性,但很难知道哪些是重要的。在从信息检索到自然语言生成的各种应用中,属性的重要性可以是有价值的信息。在本文中,我们提出了一个通用的方法,使用外部用户生成的文本数据来评估一个实体的属性的相对重要性。更具体地说,我们使用词/子词嵌入技术将外部文本数据与实体的属性名称和值进行匹配,并根据其匹配的内聚性对属性进行排名。据我们所知,这是第一个基于向量的语义匹配的重要属性识别的工作,我们的方法优于以往的传统方法。我们还将检测到的重要属性的结果应用到语言生成任务中;与以前生成的文本相比,新方法生成了更多定制和信息丰富的消息。

英文摘要:

The knowledge graph(KG) composed of entities with their descriptions and attributes, and relationship between entities, is finding more and more application scenarios in various natural language processing tasks. In a typical knowledge graph like Wikidata, entities usually have a large number of attributes, but it is difficult to know which ones are important. The importance of attributes can be a valuable piece of information in various applications spanning from information retrieval to natural language generation. In this paper, we propose a general method of using external user generated text data to evaluate the relative importance of an entity's attributes. To be more specific, we use the word/sub-word embedding techniques to match the external textual data back to entities' attribute name and values and rank the attributes by their matching cohesiveness. To our best knowledge, this is the first work of applying vector based semantic matching to important attribute identification, and our method outperforms the previous traditional methods. We also apply the outcome of the detected important attributes to a language generation task; compared with previous generated text, the new method generates much more customized and informative messages.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑