The implementation of our paper accepted by EMNLP 2021: CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs
The code and data are developed based on KGSF. Due to time reasons, it has not been transformed into a standardized code framework, so it seems that the code is bad.
python==3.6.12torch==1.3.0+cu100torch_geometric==1.3.2
python run.py --pre_train True
python run.py --train_reasoning True --learningrate 1e-4 --epoch 20
python run.py --train_rec True --learningrate 4e-4
python run.py --is_finetune True
If you find our work useful for your research, please kindly cite our paper as follows:
@inproceedings{DBLP:conf/emnlp/ZhouWHH21,
author = {Jinfeng Zhou and
Bo Wang and
Ruifang He and
Yuexian Hou},
editor = {Marie{-}Francine Moens and
Xuanjing Huang and
Lucia Specia and
Scott Wen{-}tau Yih},
title = {{CRFR:} Improving Conversational Recommender Systems via Flexible
Fragments Reasoning on Knowledge Graphs},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican
Republic, 7-11 November, 2021},
pages = {4324--4334},
publisher = {Association for Computational Linguistics},
year = {2021},
url = {https://doi.org/10.18653/v1/2021.emnlp-main.355},
doi = {10.18653/v1/2021.emnlp-main.355},
timestamp = {Thu, 16 Jun 2022 20:35:19 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/ZhouWHH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}