a-home-bird

Hello, in the process of reproducing your W2NER model, the results for datasets such as MSRA weibo are quite different from the original, can you share the following specific datasets...

How do you reproduce the NN model in the baseline

1

tag extension how to be used in few-shot. Could you please describe as detailed as possible? Thank you very much

对于您的第二个key words去偏，为什么是MASK掉文章中的关键词。

3

按照论文思路，关键词对于文章的分类带有一定的偏置倾向，可能会影响模型对于上下文的信息抽取，那么应该在key words去偏中，保留文章中的关键词，来暴露模型对于关键词的偏置，然后在最后的去偏操作中，减去。但是文章中却是MASK掉关键词，保留上下文，对于这点内容不是很理解，希望您能够给予一定的讲解，如果您百忙之中能够回邮件，不胜感谢。