多任務端對端訓練改善對話推薦

摘要

本文分析了多任務端到端Transformer模型在對話推薦任務上的表現，該任務旨在根據用戶在對話中表達的明確偏好提供推薦。儘管該領域的先前研究採用了複雜的多組件方法，其中對話管理和實體推薦任務由獨立組件處理，我們表明基於T5文本到文本Transformer模型的統一Transformer模型在推薦相關項目和生成對話對話方面可以有競爭力。我們在ReDIAL對話式電影推薦數據集上對我們的模型進行微調，並在多任務學習設置中創建源自MovieLens的額外訓練任務（例如基於輸入電影預測電影屬性和相關電影）。通過一系列探測性研究，我們展示了在額外任務中學到的知識如何轉移到對話設置中，其中每個任務都導致其相關探測分數增加了9%至52%。

English

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.

多任務端對端訓練改善對話推薦

Multi-Task End-to-End Training Improves Conversational Recommendation

摘要

Support