Paper Info
Title
Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study
Abstract
Open-domain dialog generation, which is a crucial component of artificial intelligence, is an essential and challenging problem. In this article, we present a personalized dialog system, which leverages the advantages of multitask learning and reinforcement learning for personalized dialogue generation (MRPDG). Specifically, MRPDG consists of two subtasks: 1) an author profiling module that recognizes user characteristics from the input sentence (auxiliary task) and 2) a personalized dialog generation system that generates informative, grammatical, and coherent responses with reinforcement learning algorithms (primary task). Three kinds of rewards are proposed to generate high-quality conversations. We investigate the effectiveness of three widely used reinforcement learning methods [i.e., Q-learning, policy gradient, and actor-critic (AC) algorithm] in a personalized dialog generation system and demonstrate that the AC algorithm achieves the best results on the underlying framework. Comprehensive experiments are conducted to evaluate the performance of the proposed model on two real-life data sets. Experimental results illustrate that MRPDG is able to produce high-quality personalized dialogs for users with different characteristics. Quantitatively, the proposed model can achieve better performance than the compared methods across different evaluation metrics, such as the human evaluation, BiLingual Evaluation Understudy (BLEU), and perplexity.
Year
DOI
Venue
2021
10.1109/TNNLS.2020.2975035
IEEE Transactions on Neural Networks and Learning Systems
Keywords
DocType
Volume
Author profiling,multitask learning,personalized dialog generation,reinforcement learning
Journal
32
Issue
ISSN
Citations 
1
2162-237X
1
PageRank 
References 
Authors
0.36
12
6
Name
Order
Citations
PageRank
Min Yang17720.41
Weiyi Huang211.03
Wenting Tu3859.48
Qiang Qu4397.10
Shen Ying57323.48
Lei Kai615738.17