arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.02214cs.CL
收藏

原型到风格:基于提取记忆的风格感知编辑对话生成

Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory

University of Cambridge(剑桥大学);Tencent AI Lab(腾讯人工智能实验室);The Chinese University of Hong Kong(香港中文大学)

Yixuan Su, Yan Wang, Simon Baker, Deng Cai, Xiaojiang Liu, Anna Korhonen, Nigel Collier

摘要:

对话系统在对话过程中表达预定语言风格的能力对其可用性和用户满意度有直接的积极影响。我们引入了一个新的原型到风格(PS)的框架,以应对文体对话生成的挑战。该框架使用的信息检索(IR)系统,并从检索到的响应提取响应原型。然后,文体响应生成器将原型和期望的语言风格作为模型输入,以获得高质量的文体响应。为了有效地训练所提出的模型,我们提出了一个新的风格意识的学习目标,以及去噪学习策略。在两种语言的三个基准数据集上的测试结果表明,所提出的方法在域内和跨域评估中都明显优于现有的基线

英文摘要:

The ability of a dialog system to express prespecified language style during conversations has a direct, positive impact on its usability and on user satisfaction. We introduce a new prototype-to-style (PS) framework to tackle the challenge of stylistic dialogue generation. The framework uses an Information Retrieval (IR) system and extracts a response prototype from the retrieved response. A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response. To effectively train the proposed model, we propose a new style-aware learning objective as well as a de-noising learning strategy. Results on three benchmark datasets from two languages demonstrate that the proposed approach significantly outperforms existing baselines in both in-domain and cross-domain evaluations

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑