机器学习-文本分析-5.pdfVIP

文本分析-5 分布式表示方法- 词嵌入(word embedding) How do we represent the meaning of a word ？ Definition: Meaning the idea that is represented by a word, phrase, etc. the idea that a person wants to express by using words, signs, etc the idea that is expressed in a work of writing, art, .etc 离散试表示方式的缺点(i.e. one- hot ) • 不能处理好新词 • 不能表达意思 • 没法计算两个词之间的similarity 重新回顾一下one-hot representaiton Great = [0,0,0,0,0,1,0,0,,,0] Nice = [0,0,0,0,0,0,0,1,..0] Similarity (Great, Nice) = Great * Nice = 0 However, these two words are acutally having similar meaning 有没有一种方法可以有效地