# "It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems

arXiv: https://arxiv.org/abs/2109.07576 · HTML: https://mlsanity.com/paper/2109.07576/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 15 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions](https://mlsanity.com/paper/2010.03205/) (2020)
- [Learning-to-Rank with BERT in TF-Ranking](https://mlsanity.com/paper/2004.08476/) (2020)
- [What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation](https://mlsanity.com/paper/2007.15356/) (2020)
- ["I'd rather just go to bed": Understanding Indirect Answers](https://mlsanity.com/paper/2010.03450/) (2020)
- [TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank](https://mlsanity.com/paper/1812.00073/) (2018)
- ["I'm Not Mad": Commonsense Implications of Negation and Contradiction](https://mlsanity.com/paper/2104.06511/) (2021)
- [Developing a Conversational Recommendation System for Navigating Limited Options](https://mlsanity.com/paper/2104.06552/) (2021)

## Built on by (most cited first, 3 of 3)

- [Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models](https://mlsanity.com/paper/2210.12607/) (2022)
- [Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrieval](https://mlsanity.com/paper/2308.00762/) (2023)
- [A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems](https://mlsanity.com/paper/2309.07682/) (2023)

## Abstract (arXiv)

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.