the Label Shift part is quite confusing to me and the code does not contain this part

declare-lab / dialogue-understanding

This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study

MIT License

124 stars 21 forks source link

the Label Shift part is quite confusing to me and the code does not contain this part #7

Closed yucc-leon closed 2 years ago

yucc-leon commented 2 years ago

Hi, I read about the An Empirical Study paper and don't understand what you did when during the Intra- or Inter- Speaker Shift experiment. Did you select the specific samples only with shifts happen or use some other techniques? I want to see the detail in the code but apparently they are not published. Would you please kindly explain a little?

soujanyaporia commented 2 years ago

Yes, I think @deepanwayx selected the utterances where shifted happened and specifically analyzed the model's performance for those subsets. Hope this helps.

yucc-leon commented 2 years ago

Yes, I think @deepanwayx selected the utterances where shifted happened and specifically analyzed the model's performance for those subsets. Hope this helps.

I see, thanks a lot.