search

OctoberChang / X-Transformer

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

What is the non-linear scoring function sigma to obtain final ranking? #16

Closed vinaysetty closed 3 years ago

vinaysetty commented 3 years ago

I realised you use a non-linear function called sigma to compute final ranking using the matcher score and ranker score using the OVA classifier. I didn't quite get what is this sigma function. I tried to search it in the code couldn't find it as well. Can you please define what it is?

OctoberChang commented 3 years ago

Details of the transformation function \sigma can be found in Eq(11) of the PECOS paper (https://arxiv.org/pdf/2010.05878.pdf). See the latest implementation (https://github.com/amzn/pecos/blob/mainline/pecos/xmc/base.py#L366).

vinaysetty commented 3 years ago

@OctoberChang Thanks for the answer! Can you say a bit about what is the difference to this new repository https://github.com/amzn/pecos? Do you recommend I should move to that repo for XMC?

OctoberChang commented 3 years ago

The PECOS repo (https://github.com/amzn/pecos) has the latest implementation of linear and neural models for XMC problems. Training and inference are faster, and that repo will be maintained and updated frequently.

Yes, I definitely recommend you use that repo for XMC.