A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation

TL;DR

This paper introduces a multi-task learning method that effectively uses related labeled non-dialogue text data to improve conditioned dialogue generation, addressing data scarcity issues.

Contribution

It presents a novel multi-task learning framework that jointly trains on dialogue and non-dialogue text data to enhance dialogue generation models.

Findings

Outperforms state-of-the-art models in conditioned dialogue generation

Leverages labeled non-dialogue text data effectively

Achieves significant performance improvements over previous methods

Abstract

Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage both labeled dialogue and text data. The 3 tasks jointly optimize the same pre-trained Transformer -- conditioned dialogue generation task on the labeled dialogue data, conditioned language encoding task and conditioned language generation task on the labeled text data. Experimental results show that our approach outperforms the state-of-the-art models by leveraging the labeled texts, and it also obtains larger improvement in performance comparing to the previous methods to leverage text data.