• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study
【24h】

Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study

机译：个性化对话生成的多任务学习和加固学习：实证研究

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

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.
机译：开放域对话框生成，即人工智能的一个重要组成部分，是一个重要和具有挑战性的问题。在本文中，我们介绍了一个个性化的对话系统，它利用了多任务学习和加强学习的优势，以便为个性化对话生成（MRPDG）。具体而言，MRPDG由两个子任务组成：1）一个作者分析模块，该模块从输入句（辅助任务）和2）一个个性化的对话生成系统，该生成系统从加强学习算法生成信息，语法和相干响应（主要任务）。提出了三种奖励来产生高质量的对话。我们调查三种广泛使用的强化学习方法[即Q-Learning，Policy梯度和演员 - 评论家（AC）算法]的有效性在个性化对话生成系统中，并证明了AC算法在底层框架上实现了最佳结果。进行综合实验，以评估所提出的模型对两个现实数据集的性能。实验结果表明，MRPDG能够为具有不同特征的用户生产高质量的个性化对话框。定量地，所提出的模型可以实现比不同评估指标的比较方法更好的性能，例如人类评估，双语评估升值（BLEU）和困惑。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号