arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.02094cs.CL
收藏

矢量空间词表示法的必要条件

Desiderata for Vector-Space Word Representations

University of Sheffield(谢菲尔德大学)

Leon Derczynski

摘要:

目前有大量的词的向量空间表示,而且还在不断增长。这些由包含实值的固定长度向量组成,表示一个单词。结果是一个表示,许多传统的信息处理和数据采掘技术的力量可以承担,只要表示设计有一些预见性,并符合一定的约束。本文详细介绍了词的向量空间表示的设计要求。

英文摘要:

A plethora of vector-space representations for words is currently available, which is growing. These consist of fixed-length vectors containing real values, which represent a word. The result is a representation upon which the power of many conventional information processing and data mining techniques can be brought to bear, as long as the representations are designed with some forethought and fit certain constraints. This paper details desiderata for the design of vector space representations of words.

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。

↑