结合对话状态信息的个性化对话回复生成
Personalized Dialogue Response Generation Combined with Conversation State Information
桂海涛 1王中卿1
作者信息
- 1. 苏州大学计算机科学与技术学院 江苏苏州 215006
- 折叠
摘要
尽管个性化回复生成模型取得了显著成功,但这些研究都未能很好地考虑到对话状态信息对于个性化对话回复的影响.针对此问题,基于预训练生成模型提出了结合对话状态的自监督对话回复生成模型,该模型可以有效地对结合对话状态生成个性化的回复.首先,将对话状态纳入情景喜剧数据集中,以增强模型对上下文信息的理解能力.其次,采用自监督的训练技术,赋予预训练语言生成模型独特的对话文本特征知识,并采用多种掩码策略合并对话文本和对话状态,进一步提升模型性能.最后,基于历史对话,使用自监督生成模型生成个性化回复.在自行收集的情景喜剧数据集上进行性实验,结果表明,结合对话状态的对话回复生成模型在多项指标上优于一些强基准,进而证明了对话状态和个性化回复生成模型的有效性.
Abstract
Despite the significant achievements in personalized response generation models,existing studies have not adequately considered the impact of dialogue state information on personalized dialogue responses.To address this issue,this paper proposes a self-supervised dialogue response generation model that incorporates dialogue state to effectively generate personalized replies based on pre-trained generative models.Firstly,we integrate the dialogue state into a situational comedy dataset to enhance the model's contextual understanding.Secondly,we employ self-supervised training techniques to imbue the pre-trained language ge-neration model with unique dialogue text features and employ various masking strategies to combine dialogue text and dialogue state,further enhancing model performance.Lastly,leveraging historical dialogues,we utilize the self-supervised generative model to produce personalized responses.Experimental results on a self-collected situational comedy dataset demonstrate that the dia-logue response generation model incorporating dialogue state outperforms several strong baselines across multiple metrics,thus validating the effectiveness of incorporating dialogue state in personalized response generation models.
关键词
对话回复/对话状态/自监督/预训练/文本生成Key words
Dialogue response/Conversation state/Self-supervision/Pre-training/Text generation引用本文复制引用
基金项目
国家自然科学基金(61806137)
国家自然科学基金(61702149)
出版年
2024
NETL
NSTL
万方数据