“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems

Victor Bursztyn, Jennifer Healey, Nedim Lipka, Eunyee Koh, Doug Downey, Larry Birnbaum


Abstract
Conversations aimed at determining good recommendations are iterative in nature. People often express their preferences in terms of a critique of the current recommendation (e.g., “It doesn’t look good for a date”), requiring some degree of common sense for a preference to be inferred. In this work, we present a method for transforming a user critique into a positive preference (e.g., “I prefer more romantic”) in order to retrieve reviews pertaining to potentially better recommendations (e.g., “Perfect for a romantic dinner”). We leverage a large neural language model (LM) in a few-shot setting to perform critique-to-preference transformation, and we test two methods for retrieving recommendations: one that matches embeddings, and another that fine-tunes an LM for the task. We instantiate this approach in the restaurant domain and evaluate it using a new dataset of restaurant critiques. In an ablation study, we show that utilizing critique-to-preference transformation improves recommendations, and that there are at least three general cases that explain this improved performance.
Anthology ID:
2021.emnlp-main.145
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1913–1918
Language:
URL:
https://aclanthology.org/2021.emnlp-main.145
DOI:
10.18653/v1/2021.emnlp-main.145
Bibkey:
Cite (ACL):
Victor Bursztyn, Jennifer Healey, Nedim Lipka, Eunyee Koh, Doug Downey, and Larry Birnbaum. 2021. “It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1913–1918, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems (Bursztyn et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.145.pdf
Software:
 2021.emnlp-main.145.Software.zip
Video:
 https://preview.aclanthology.org/improve-issue-templates/2021.emnlp-main.145.mp4
Code
 vbursztyn/critique-to-preference-emnlp2021