[1802.05365] Deep contextualized word representations
5
公开标注数
5
参与人数
2026-07-17 10:05:51
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-17 13:26:51
原文高亮摘录
“NAACL 2018. Originally posted to openreview 27 Oct 2017. v2 updated for NAACL camera ready”
Whisper 随想笔记
Wait, so the camera ready is the same as the arXiv v2? Cool, that's helpful to know.
划选高亮2026-07-17 13:17:51
原文高亮摘录
“NAACL 2018. Originally posted to openreview 27 Oct 2017. v2 updated for NAACL camera ready”
Whisper 随想笔记
Man, I remember when this hit openreview back in 2017, feels like forever ago.
划选高亮2026-07-17 10:23:51
原文高亮摘录
“models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts”
Whisper 随想笔记
I wonder if this actually helps with rare words or just common ambiguous ones.
划选高亮2026-07-17 10:14:51
原文高亮摘录
“models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts”
Whisper 随想笔记
Wait, so they're basically pre-training a language model and reusing its internals?
划选高亮2026-07-17 10:05:51
原文高亮摘录
“models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts”
Whisper 随想笔记
Finally someone tackling polysemy instead of just static vectors!
分享本页 Whisper
短链接
https://domwhisper.com/s/bc4b6b0734bd嵌入代码
<iframe src="https://domwhisper.com/embed/bc4b6b0734bd" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>