search

OctoberChang / X-Transformer

X-Transformer: Taming Pretrained Transformers for eXtreme Multi-label Text Classification
BSD 3-Clause "New" or "Revised" License
135 stars 28 forks source link

about the dataset #14

Closed Liyx98 closed 3 years ago

Liyx98 commented 3 years ago

Hi~There are something wrong as I run the code to get the datasets. So would you please give me a link to the datasets or send them to me as a file? thank you.

OctoberChang commented 3 years ago

You can also download the datasets from AttentionXML repo (https://github.com/yourh/AttentionXML), which is the same training/test set we are using. Sometimes there are download capacity limits in the goolge drive, you may try multiple times.

Liyx98 commented 3 years ago

Thank you very much for your reply.

shunshun-lala commented 2 years ago

Hi, I have also found something wrong when I tried to get the data set. I read this comment and I'm confused about the difference between your datasets and ones from AttentionXML. There are no files named label_map.txt and files with postfix npz in the latter. How can I get these files? Thanks for your reply!

shunshun-lala commented 2 years ago

Hi, I'm wondering how you generate the file X.trn.npz, i.e. the instance TF-IDF feature matrix for the train set? Could you share your code about this process? Or is there any public code which have the same function? Thanks a lot!