原书出处
Natural Language Processing in Action, Second Edition
There are two kinds of word embeddings you may encounter in the real world: static and contextualized. Static word embeddings can be used on individual words or n-grams in isolation, and once the training is completed, the vectors remain fixed. These are the kinds of word embeddings you’ll use for analogy and other word vector reasoning problems you want to solve. You’ll train a language
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