-
Notifications
You must be signed in to change notification settings - Fork 114
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Any sources for the click model based relabeling mentioned in the readme #63
Comments
If you're asking about some literature sources about click models in LTR in general, then look at Seq2Slate paper https://arxiv.org/pdf/1810.02019.pdf (mentioned in https://github.com/allegro/allRank/blob/master/allrank/click_models/cascade_models.py#L37C51-L37C83) which explains a procedure of using a reasonable click to obtain click-through data programatically. This click model is implemented as well as some dummy click models like random-click, and as well as some raw ideas about some more complex click-models |
All the click models implemented are located in click_models module with some short explanation in docstrings. As mentioned in the part of readme you’ve referred to, before applying a click model you need to pass previously trained allRank model and pass it to rank_and_click.py script with its config modified by specifying click model (along with its arguments) you want to apply - that is because some click models (e. g. cascade model) need relevance (output of the model) to decide which item to click. |
Was going through the readme and found this
The click model that is mentioned here seems interesting
any references for the method mentioned here would be great.
The text was updated successfully, but these errors were encountered: