Automatic Generation of Natural Language Explanations

By Felipe Soares Da Costa, Sixun Ouyang, Peter Dolog, Aonghus Lawlor. 2017

109 citations recorded by the source corpus.

An interesting challenge for explainable recommender systems is to provide successful interpretation of recommendations using structured sentences. It is well known that user-generated reviews, have strong influence on the users' decision. Recent techniques exploit user reviews to generate natural language explanations. In this paper, we propose a character-level attention-enhanced long short-term memory model to generate natural language explanations. We empirically evaluated this network using two real-world review datasets. The generated text present readable and similar to a real user's writing, due to the ability of reproducing negation, misspellings, and domain-specific vocabulary.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Chen
2. Yongfeng Zhang
3. Hanxiong Chen
4. Le Wu
5. Xing Xie
6. Shaoyun Shi
7. Xiting Wang
8. Hao Fu

In Computer Vision and Pattern Recognition

1. Yongfeng Zhang
2. Xu Chen
3. Hanxiong Chen
4. Xing Xie
5. Hao Fu
6. Tetsuya Sakai
7. Shaoyun Shi
8. Xiting Wang

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, background): “However, explanations can also help to improve the trustworthiness (Cramer et al. [2008]), efficiency (Tintarev and Masthoff [2011]), diversity (Yu et al. [2009]), satisfaction (Bilgic and Mooney [2005]), and scrutability of the system (Knijnenburg et al.”
• Personalized Reason Generation for Explainable Song Recommendation (2019, background): “Costa et al. [51] attempt to summarize items’ review sentences as explanations by learning large-scale review data.”
• A Reinforcement Learning Framework for Explainable Recommendation (2018, background): “Recently, researchers also proposed methods that automatically generate natural language sentences word-by-word [20], [34].”
• Generate Natural Language Explanations for Recommendation (2021, methodology): “To alleviate the problem, Costa et al [5] a empted to train generation models based on user reviews and automatically generate fake reviews as explanations.”