思想与社会2018 · 分享于 Hacker News
BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding
探索《BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
评论 #48363283 帖子正文 #41491707 评论 #40893841 评论 #39381802 评论 #38075614 评论 #38011389 评论 #37423279 评论 #36574439 评论 #36162724 评论 #35375774 评论 #35077337 评论 #34710267 评论 #33915317 评论 #33537561 评论 #25778301 评论 #22006942 评论 #20758743 评论 #20749275 评论 #19504256 评论 #19269257 评论 #19262990 评论 #19182053 评论 #19165225 评论 #19164697 评论 #19073575 评论 #18352518 评论 #18352253
Ymmq ·
Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing Award
773 赞同146 评论
Yvincent_s ·
OpenAI – Application for US trademark “GPT” has failed
602 赞同259 评论
Yputtycat ·
Machine Learning: The Great Stagnation
484 赞同218 评论
Yhiphipjorge ·
The Unreasonable Effectiveness of Deep Feature Extraction
324 赞同55 评论
Yxcodevn ·
GPT-2: 6-Month Follow-Up
160 赞同93 评论
Ysachaarbonel ·
Building a semantic search engine in Rust
136 赞同27 评论
YArtWomb ·
TensorFlow Code for Google Research's BERT: Pre-Training Method for NLP Tasks
129 赞同13 评论
Ynshm ·
Microsoft’s New MT-DNN Outperforms Google BERT
121 赞同38 评论
Ytheafh ·
Google Research: Looking Back at 2019, and Forward to 2020 and Beyond
96 赞同14 评论
Ymoondistance ·
New AI Training Technique Is Drastically Faster, Says Google
84 赞同38 评论
Yandreyk ·
Beyond Local Pattern Matching: Recent Advances in Machine Reading
80 赞同18 评论
Yliviosoares ·
BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding
78 赞同5 评论
Ykartayyar ·
Generalized Language Models
40 赞同3 评论
YMurizS ·
AlphaCode Attention Visualization
23 赞同7 评论
YEGreg ·
Google internally developed chatbots like ChatGPT years ago
7 赞同2 评论
Ydragonmouse ·
Ask HN: How to Break into AI Engineering
7 赞同1 评论
Ymelvinmelih ·
Show HN: Turn Any ArXiv Paper into a 200-Page Prerequisite Reading Book
6 赞同3 评论
Yjohncole ·
Ernie, China's ChatGPT, Cracks Under Pressure
4 赞同1 评论
Yghosthamlet ·
Dissecting Bert
3 赞同1 评论
Ychatmasta ·
Google trained Bard on ChatGPT chats from ShareGPT
3 赞同1 评论
Ythoughtpeddler ·
Superintelligence: The Idea That Eats Smart People (2016)
3 赞同0 评论
Yalan-stark ·
What were the 40 research papers on the list Ilya Sutskever gave John Carmack?
2 赞同0 评论
Ysimonw ·
Embeddings: What they are and why they matter
2 赞同0 评论
Yskadamat ·
Ask HN: Why is OpenAI still called OpenAI?
2 赞同2 评论
Ymusha68k ·
Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding
1 赞同0 评论
Ymontebicyclelo ·
Notes on training BERT from scratch on an 8GB consumer GPU
1 赞同0 评论