Word2vec - Wikipedia
5
公开标注数
5
参与人数
2026-07-17 10:03:07
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-17 13:24:07
原文高亮摘录
“skip-gram and CBOW are exactly the same in architecture. They only differ in the objective function during training.”
Whisper 随想笔记
So the magic is all in the loss function, neat.
划选高亮2026-07-17 13:15:07
原文高亮摘录
“skip-gram and CBOW are exactly the same in architecture. They only differ in the objective function during training.”
Whisper 随想笔记
Huh, I always thought they had different layers too, good to know.
划选高亮2026-07-17 10:21:07
原文高亮摘录
“Word2vec is a technique in natural language processing for obtaining vector representations of words.”
Whisper 随想笔记
Cool, but does it actually handle polysemy well or just average meanings?
划选高亮2026-07-17 10:12:07
原文高亮摘录
“Word2vec is a technique in natural language processing for obtaining vector representations of words.”
Whisper 随想笔记
I remember when this came out, it was a game changer for NLP research.
划选高亮2026-07-17 10:03:07
原文高亮摘录
“Word2vec is a technique in natural language processing for obtaining vector representations of words.”
Whisper 随想笔记
So word2vec is basically how computers learn word meanings from context, right?
分享本页 Whisper
短链接
https://domwhisper.com/s/fa0d2734c92a嵌入代码
<iframe src="https://domwhisper.com/embed/fa0d2734c92a" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>