Item-based Collaborative Filtering with BERT

Tian Wang, Yuyangzi Fu


Abstract
In e-commerce, recommender systems have become an indispensable part of helping users explore the available inventory. In this work, we present a novel approach for item-based collaborative filtering, by leveraging BERT to understand items, and score relevancy between different items. Our proposed method could address problems that plague traditional recommender systems such as cold start, and “more of the same” recommended content. We conducted experiments on a large-scale real-world dataset with full cold-start scenario, and the proposed approach significantly outperforms the popular Bi-LSTM model.
Anthology ID:
2020.ecnlp-1.8
Volume:
Proceedings of The 3rd Workshop on e-Commerce and NLP
Month:
July
Year:
2020
Address:
Seattle, WA, USA
Venues:
ACL | ECNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
54–58
Language:
URL:
https://www.aclweb.org/anthology/2020.ecnlp-1.8
DOI:
10.18653/v1/2020.ecnlp-1.8
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.ecnlp-1.8.pdf
Video:
 http://slideslive.com/38931249