原书出处
Natural Language Processing in Action, Second Edition
The list of all the unique words in a document or corpus is called its vocabulary or lexicon. Creating your vocabulary is one of the most important steps in your NLP pipeline. If you don’t identify a particular token and give it a place to be stored, your pipeline will completely ignore it. In most NLP pipelines, you will define a single token named <OOV>
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-3.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36