Papers by Yeongseo Jung
Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that use separate recommendation and dialogue modules produce inconsistent results . a multi-task learning model is proposed to bridge the gap between recommendation and generated responses . |
| Approach: | They propose a multi-task learning model that integrates knowledge from two teachers and selectively gates between them via Contextualized Knowledge Distillation. |
| Outcome: | The proposed model significantly improves recommendation performance while enhancing fluency and achieves comparable results in terms of diversity. |