Skip to content

Code and runs for the ECIR 2021 paper "User Engagement Prediction for Clarification in Search".

License

Notifications You must be signed in to change notification settings

isekulic/mimics-EL-benchmark

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

mimics-EL-benchmark

Code and runs for the ECIR 2021 paper "User Engagement Prediction for Clarification in Search".

Download dataset

You can download the preprocessed MIMICS-Click with mapped SERP elements for each query from here.

Training

Run run_mimics.py with wanted parameters. Parameters are described in the run_mimics.py file.

Testing

Download the checkpoints used in the paper here. You can then run the prediction with:

python run_mimics.py --mode 'test' --test_ckpt '_ckpt_epoch_0_v6.ckpt' --text_input 'qqat'

Citation

Please cite the following if you found our paper or these resources useful.

@inproceedings{sekulic-2021-user,
  author    = {Ivan Sekuli{\'c}
                and Mohammad Aliannejadi
                and Fabio Crestani},
  title     = {User Engagement Prediction for Clarification in Search},
  booktitle = {Advances in Information Retrieval - 43rd European Conference on {IR} Research, 
    {ECIR} 2021, Virtual Event, March 28 - April 1, 2021, Proceedings},
  year      = {2021}
}

About

Code and runs for the ECIR 2021 paper "User Engagement Prediction for Clarification in Search".

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages