arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.07295cs.CLcs.IRstat.AP
收藏

基于分布式语言表示倒置的文档分类

Document Classification by Inversion of Distributed Language Representations

University of Chicago Booth School of Business(芝加哥大学布斯商学院)

Matt Taddy

摘要:

最近在分布式语言模型的结构和度量方面取得了许多进展:这些模型从单词映射到富含单词选择和组成信息的向量空间。这个向量空间是分布式语言表示。本文的目的是指出,任何分布式表示都可以通过贝叶斯规则的反演转换为分类器。该方法是简单和模块化的,因为它将与任何语言表示一起工作,其训练可以被公式化为优化概率模型。在我们对来自Yelp评论的200万个句子的应用中,我们还发现它的性能与复杂的专用算法一样好,甚至更好。

英文摘要:

There have been many recent advances in the structure and measurement of distributed language models: those that map from words to a vector-space that is rich in information about word choice and composition. This vector-space is the distributed language representation. The goal of this note is to point out that any distributed representation can be turned into a classifier through inversion via Bayes rule. The approach is simple and modular, in that it will work with any language representation whose training can be formulated as optimizing a probability model. In our application to 2 million sentences from Yelp reviews, we also find that it performs as well as or better than complex purpose-built algorithms.

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。

↑