If you are interested in building up your research on this work, please cite:
@inproceedings{sanner:www20,
author = {Kai Luo and Scott Sanner and Ga Wu and Hanze Li and Hojin Yang},
title = {Latent Linear Critiquing for Conversational Recommender Systems},
year = {2020},
booktitle = {Proceedings of the 29th International Conference on the World Wide Web (WWW-20)},
address = {Taipei, Taiwan},
url_paper = {https://ssanner.github.io/papers/www20_llc.pdf}
}
- LP Option1
- LP Option2
- LP Option3
- Amazon CDs&Vinyl,
- Beer Advocate,
We don't have rights to release the datasets. Please ask permission from Professor Julian McAuley.
Please refer to the preprocess
folder for preprocessing raw datasets steps.
Keyphrases we used are not necessarily the best. If you are interested in how we extracted those keyphrases, please refer to the preprocess
folder. If you are interested in what keyphrases we extracted, please refer to the data
folder.
python reproduce_critiquing.py --data_dir "data/beer/" --dataset_name beer/ --save_path beer/critiquing_results.csv --num_users_sampled 10 --critiquing_model_name LP1Simplified