End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System
End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System
复制标题
未经修饰的多角色对话系统中端到端个性化幽默响应的生成
DOI：
10.1109/access.2019.2926830
复制
发表时间：
2019
期刊：
影响因子：
3.9
通讯作者：
Changjian Hu
中科院分区：
文献类型：
--
作者：
Qichuan Yang;Zhiqiang He;Zhiqiang Zhan;Rang Li;Yanwei Lee;Yang Zhang;Changjian Hu
多角色对话是自然语言处理中的一个难题，它不仅需要理解句子，还需要模拟角色之间的交互。然而，现有的方法假设只有两个扬声器存在于对话中。在真实的生活中，这种假设并不总是有效的。更多的时候，有多个发言者参与。为了解决这个问题，我们提出了一个多角色插入对话系统（MIDS），根据对话上下文和下一个扬声器预测产生合理的反应。MIDS采用多重角色定义编码器来理解每个说话人，并使用独立的序列模型来预测下一个说话人。独立序列模型还用作控制器以将编码器与权重集成。然后，注意力增强解码器基于对话上下文、说话者预测和集成编码器生成响应。此外，在独特的说话人预测的帮助下，MIDS能够生成不同的响应，并允许自己在适当的时候加入（加入）对话。此外，一个新的奖励函数和强化学习（RL）的更新策略被应用到MIDS，这进一步使MIDS的能力，写剧本。实验结果表明，MIDS在提高说话人预测准确率和减少响应生成困惑方面有显著的效果。它还能够在现实生活中的在线对话中与用户进行无提示的交互，并在生成脚本时避免无意义的对话循环。这篇论文标志着多角色幽默对话生成的第一步。
Multi-role dialogue is challenging in natural language processing (NLP), which needs not only to understand sentences but also to simulate interaction among roles. However, the existing methods assume that only two speakers are present in a conversation. In real life, this assumption is not always valid. More often, there are multiple speakers involved. To address this issue, we propose a multi-role interposition dialogue system (MIDS) that generates reasonable responses based on the dialogue context and next speaker prediction. The MIDS employs multiply role-defined encoders to understand each speaker and an independent sequence model to predict the next speaker. The independent sequence model also works as a controller to integrate encoders with weights. Then, an attention-enhanced decoder generates responses based on the dialogue context, speaker prediction, and integrated encoders. Moreover, with the help of unique speaker prediction, the MIDS is able to generate diverse responses and allow itself to join (interpose) the conversation when appropriate. Furthermore, a novel reward function and an updating policy of reinforcement learning (RL) are applied to the MIDS, which further enable MIDS the ability to write drama scripts. The experimental results demonstrate that the MIDS offers a significant improvement to the accuracy of speaker prediction and the reduction of response generation perplexity. It is also able to interact with users without cues during real-life online conversations and avoid meaningless conversation loops while generating scripts. This paper marks the first step toward multi-role humorous dialogue generation.