首页> 外文期刊>Journal of Intelligent Information Systems >EVE: explainable vector based embedding technique using Wikipedia
【24h】

EVE: explainable vector based embedding technique using Wikipedia

机译:夏娃:使用维基百科的可解释基于向量的嵌入技术

获取原文
获取原文并翻译 | 示例
           

摘要

We present an unsupervised explainable vector embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a concept using human-readable labels, thereby it is readily interpretable. Specifically, each vector is constructed using the Wikipedia category graph structure together with the Wikipedia article link structure. To test the effectiveness of the proposed model, we consider its usefulness in three fundamental tasks: 1) intruder detection-to evaluate its ability to identify a non-coherent vector from a list of coherent vectors, 2) ability to cluster-to evaluate its tendency to group related vectors together while keeping unrelated vectors in separate clusters, and 3) sorting relevant items first-to evaluate its ability to rank vectors (items) relevant to the query in the top order of the result. For each task, we also propose a strategy to generate a task-specific human-interpretable explanation from the model. These demonstrate the overall effectiveness of the explainable embeddings generated by EVE. Finally, we compare EVE with the Word2Vec, FastText, and GloVe embedding techniques across the three tasks, and report improvements over the state-of-the-art.
机译:我们介绍了一个不可思议的可解释的媒体嵌入技术,称为夏娃,该技术建立在维基百科的结构之上。所提出的模型定义了使用人可读标签表示概念的语义矢量的尺寸,从而易于解释。具体地,使用维基百科类图形结构与维基百科文章链接结构一起构建每个矢量。为了测试所提出的模型的有效性,我们认为其三个基本任务中的有用性:1)入侵者检测 - 评估其从连贯的矢量列表中识别非相干载体,2)集群的能力 - 评估其将相关载体的趋势在一起,同时保持不同的群集中的不相关的矢量,以及3)首先对相关项目进行排序 - 以评估其在结果的最高阶数中对查询相关的向量(项目)的能力。对于每项任务,我们还提出了一种从模型中生成特定的任务的人类可解释解释的策略。这些证明了前夕产生的可解释的嵌入的整体效果。最后,我们将夏娃与三个任务中的Word2VEC,FastText和手套嵌入技术进行比较,并报告最先进的改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号