Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation
This addresses bias mitigation in conversational recommendation systems, which is an incremental improvement for researchers and developers in this domain.
The paper tackles biases in conversational recommendation systems by analyzing selection and popularity biases in benchmark datasets and proposing two data augmentation strategies called 'Once-Aug' and 'PopNudge'. The results show consistent improvements on ReDial and TG-ReDial datasets, though specific numerical gains are not provided.
Conversational Recommendation System (CRS) is a rapidly growing research area that has gained significant attention alongside advancements in language modelling techniques. However, the current state of conversational recommendation faces numerous challenges due to its relative novelty and limited existing contributions. In this study, we delve into benchmark datasets for developing CRS models and address potential biases arising from the feedback loop inherent in multi-turn interactions, including selection bias and multiple popularity bias variants. Drawing inspiration from the success of generative data via using language models and data augmentation techniques, we present two novel strategies, 'Once-Aug' and 'PopNudge', to enhance model performance while mitigating biases. Through extensive experiments on ReDial and TG-ReDial benchmark datasets, we show a consistent improvement of CRS techniques with our data augmentation approaches and offer additional insights on addressing multiple newly formulated biases.