Multi-Task End-to-End Training Improves Conversational Recommendation
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 generation 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Conversational RecommendationDialogue GenerationMovie RecommendationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-Task End-to-End Training Improves Conversational Recommendation
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 i…
Conversational RecommendationDialogue ManagementManagementMovie RecommendationTowards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation
In Conversational Recommendation System (CRS), an agent is asked to recommend a set of items to users within natural language conversations. To address the need for both conversational capability and personalized recomme…
Conversational RecommendationDiversityKnowledge DistillationMulti-Task LearningOn Estimating the Training Cost of Conversational Recommendation Systems
Conversational recommendation systems have recently gain a lot of attention, as users can continuously interact with the system over multiple conversational turns. However, conversational recommendation systems are based…
Conversational RecommendationKnowledge DistillationRecommendation SystemsTalk the Walk: Synthetic Data Generation for Conversational Music Recommendation
Recommender systems are ubiquitous yet often difficult for users to control, and adjust if recommendation quality is poor. This has motivated conversational recommender systems (CRSs), with control provided through natur…
Language ModellingMusic RecommendationRecommendation SystemsRetrieval+1DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation
In this paper, we provide a bilingual parallel human-to-human recommendation dialog dataset (DuRecDial 2.0) to enable researchers to explore a challenging task of multilingual and cross-lingual conversational recommendat…
Conversational Recommendation