原书出处
Natural Language Processing in Action, Second Edition
Fortunately, greedy search and repetition filtering are not the only approaches you can take to generate the next token. Two ways to make the token decoding both less predictable and less noisy (incorrect) are beam search and sampling. Beam search keeps track of several possible “beams” or paths through the fishbone diagram. That way, you can you can choose the words with the maximum total
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-10.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36