Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Multi-Task End-to-End Training Improves Conversational Recommendation
arXiv (Cornell University)
08 May 2023
Abstract
In this paper, we analyze the performance of a multitask end-to-end
transformer model on the task of conversational recommendations, which aim to
provide recommendations based on a user's explicit preferences expressed in
dialogue. While previous works in this area adopt complex multi-component
approaches where the dialogue management and entity recommendation tasks are
handled by separate components, we show that a unified transformer model, based
on the T5 text-to-text transformer model, can perform competitively in both
recommending relevant items and generating conversation dialogue. We fine-tune
our model on the ReDIAL conversational movie recommendation dataset, and create
additional training tasks derived from MovieLens (such as the prediction of
movie attributes and related movies based on an input movie), in a multitask
learning setting. Using a series of probe studies, we demonstrate that the
learned knowledge in the additional tasks is transferred to the conversational
setting, where each task leads to a 9%-52% increase in its related probe score.
Metrics
12 Record Views
Details
- Title
- Multi-Task End-to-End Training Improves Conversational Recommendation
- Creators
- Naveen RamDima KuzminEllie Ka In ChioMoustafa Farid AlzantotSantiago OntanonAmbarish JashJudith Yue Li
- Publication Details
- arXiv (Cornell University)
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science
- Other Identifier
- 991021869013904721