Topic models for taxonomies
Topic models for taxonomies
复制标题
DOI：
10.1145/2232817.2232861
复制
发表时间：
2012-06
期刊：
影响因子：
--
通讯作者：
A. Bakalov;A. McCallum;Hanna M. Wallach;David Mimno
中科院分区：
文献类型：
--
作者：
A. Bakalov;A. McCallum;Hanna M. Wallach;David Mimno
概念分类法，如网格，ACM计算分类系统，和纽约时报主题标题经常被用来帮助组织数据。它们通常由一组按层次结构组织的概念名称组成。但是，这些名称和结构通常不足以完全捕获分类法节点的预期含义，特别是非专家可能难以导航和将数据放入分类法中。本文介绍了两个半监督主题模型，它们通过利用多标签文档的语料库，自动地用许多额外的关键字增加给定的分类法。我们的实验表明，用户发现主题有利于分类解释，大大提高了他们的编目准确性。此外，与Labeled LDA相比，该模型提供了更好的信息率。
Concept taxonomies such as MeSH, the ACM Computing Classification System, and the NY Times Subject Headings are frequently used to help organize data. They typically consist of a set of concept names organized in a hierarchy. However, these names and structure are often not sufficient to fully capture the intended meaning of a taxonomy node, and particularly non-experts may have difficulty navigating and placing data into the taxonomy. This paper introduces two semi-supervised topic models that automatically augment a given taxonomy with many additional keywords by leveraging a corpus of multi-labeled documents. Our experiments show that users find the topics beneficial for taxonomy interpretation, substantially increasing their cataloging accuracy. Furthermore, the models provide a better information rate compared to Labeled LDA.