原书出处
Natural Language Processing in Action, Second Edition
Here’s how our token sorter fits into an NLP pipeline right after a tokenizer (see chapter 2). We have included a stop word filter as well as a rare word filter in our mechanical token sorter sketch illustrated in figure 1.6. Strings flow in from the top, and BOW vectors are created from the height profile of the token “stacks” at the bottom.
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-1.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36