← 返回卡片

原书出处

Natural Language Processing in Action, Second Edition

Second Edition · 核验版本的摘录快照 · 导入于 2026-11-14T20:22:29.266Z

Decoders The decoder is nearly identical to the encoder but has three sublayers instead of two. The new sublayer is a fully connected layer similar to the multi-head self-attention matrix, but the new sublayer contains only zeros and ones. This creates a masking of the output sequences to the right of the current target token (in a left-to-right language, like English). This ensures that predictions

此预览只包含定位所需的摘录和上下文。

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-9.html

EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36