Subjective Attributes in Conversational Recommendation Systems: Challenges and Opportunities
Abstract
The ubiquity of recommender systems has increased the need for higher-bandwidth, natural and efficient communication with users. This need is increasingly filled by recommenders that support natural language interaction, often conversationally. Given the inherent semantic subjectivity present in natural language, we argue that modeling subjective attributes in recommenders is a critical, yet understudied, avenue of AI research. We propose a novel framework for understanding different forms of subjectivity, examine various recommender tasks that will benefit from a systematic treatment of subjective attributes, and outline a number of research challenges.
Cite
Text
Radlinski et al. "Subjective Attributes in Conversational Recommendation Systems: Challenges and Opportunities." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21492Markdown
[Radlinski et al. "Subjective Attributes in Conversational Recommendation Systems: Challenges and Opportunities." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/radlinski2022aaai-subjective/) doi:10.1609/AAAI.V36I11.21492BibTeX
@inproceedings{radlinski2022aaai-subjective,
title = {{Subjective Attributes in Conversational Recommendation Systems: Challenges and Opportunities}},
author = {Radlinski, Filip and Boutilier, Craig and Ramachandran, Deepak and Vendrov, Ivan},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {12287-12293},
doi = {10.1609/AAAI.V36I11.21492},
url = {https://mlanthology.org/aaai/2022/radlinski2022aaai-subjective/}
}