
比赛/项目 经验分享
比赛/项目经验分享
Jay_Tang
小唐的 ML & NLP 进阶之路
展开
-
Kaggle: Jigsaw Multilingual Toxic Comment Classification Top Solutions 金牌思路总结
Before we start Two of my previous post might be helpful in getting a general understanding of the top solutions of this competition. Please feel free to check them out. Knowledge Distillation clearly explained Common Multilingual Language Modeling method原创 2020-08-11 08:45:49 · 2552 阅读 · 0 评论 -
Kaggle: Tweet Sentiment Extraction 方法总结 Part 2/2: 金牌思路总结
Before we start I attended two NLP competition in June, Tweet Sentiment Extraction and Jigsaw Multilingual Toxic Comment Classification, and I’m happy to be a Kaggle Expert from now on ???? Tweet Sentiment Extraction Goal: The objective in this competitio原创 2020-07-01 12:07:22 · 1233 阅读 · 9 评论 -
Kaggle: Tweet Sentiment Extraction 方法总结 Part 1/2: 常用方法总结
文章目录往期文章目录链接NoteBefore we startTweet Sentiment ExtractionWhat is the MAGIC?Common MethodsLabel SmoothingImplementation of Label SmoothingIn tensorflowIn pytorchMulti-sample dropoutImplementationStochastic Weight Averaging (SWA)Different learning rate setti原创 2020-07-01 12:06:29 · 2220 阅读 · 2 评论 -
Kaggle: Google Quest Q&A Labeling 首战银牌方法总结+心得
fesfeee原创 2020-04-04 06:18:57 · 1348 阅读 · 0 评论