Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering

Reinald Adrian Pugoy, Hung-Yu Kao


Abstract
We pioneer the first extractive summarization-based collaborative filtering model called ESCOFILT. Our proposed model specifically produces extractive summaries for each item and user. Unlike other types of explanations, summary-level explanations closely resemble real-life explanations. The strength of ESCOFILT lies in the fact that it unifies representation and explanation. In other words, extractive summaries both represent and explain the items and users. Our model uniquely integrates BERT, K-Means embedding clustering, and multilayer perceptron to learn sentence embeddings, representation-explanations, and user-item interactions, respectively. We argue that our approach enhances both rating prediction accuracy and user/item explainability. Our experiments illustrate that ESCOFILT’s prediction accuracy is better than the other state-of-the-art recommender models. Furthermore, we propose a comprehensive set of criteria that assesses the real-life explainability of explanations. Our explainability study demonstrates the superiority of and preference for summary-level explanations over other explanation types.
Anthology ID:
2021.acl-long.232
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2981–2990
Language:
URL:
https://aclanthology.org/2021.acl-long.232
DOI:
10.18653/v1/2021.acl-long.232
Bibkey:
Cite (ACL):
Reinald Adrian Pugoy and Hung-Yu Kao. 2021. Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2981–2990, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering (Pugoy & Kao, ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.232.pdf
Video:
 https://aclanthology.org/2021.acl-long.232.mp4
Code
 reinaldncku/escofilt