Information Processing & Management ( IF 8.6 ) Pub Date : 2021-04-23 , DOI: 10.1016/j.ipm.2021.102605 Haifeng Sun , Daixuan Cheng , Jingyu Wang , Qi Qi , Jianxin Liao
Controllable response generation is an attractive and valuable task to the success of conversational systems. However, controlling both pattern and content of the response has not been well studied in existing models since they are mainly based on matching mechanisms. To tackle the problem, we first design a pattern model to automatically learn and extract speech patterns from words. The pattern is then integrated into the encoder–decoder model to control the response pattern. Second, a sentence sampling algorithm is built to directly insert or delete words in the generated response, so that the content is controlled. In this two-stage framework, the response could be explicitly controlled by the pattern and content, without any human annotation of the post-response dataset. Experiments show the proposed framework achieves better performance in response controllability than the state-of-the-art.
中文翻译:
模式和内容控制的响应生成
对于会话系统的成功而言,可控的响应生成是一项有吸引力且有价值的任务。但是,在现有模型中,控制响应的模式和内容都没有得到很好的研究,因为它们主要基于匹配机制。为了解决这个问题,我们首先设计一种模式模型,以自动学习和从单词中提取语音模式。然后将该模式集成到编码器-解码器模型中,以控制响应模式。其次,构建句子采样算法以直接在生成的响应中插入或删除单词,从而控制内容。在此两阶段框架中,响应可以由模式和内容显式控制,而无需任何人工注释后响应数据集。