原书出处
Natural Language Processing in Action, Second Edition
In previous chapters, you could ignore the nearby context of a word. All you needed to do was count up the uses of a word within the same document. It turns out, if you make your documents very, very short, these counts of co-occurrences become useful for representing the meaning of words themselves. This was the key innovation of Tomas Mikolov and his Word2Vec NLP
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-6.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36