一种用于多轮对话生成的静态与动态注意力框架
A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
AI总结：
针对多轮对话历史建模中基于 RNN 的层级编码存在梯度消失的问题，本文提出融合静态与动态注意力的框架，并在 Ubuntu 和 Opensubtitles 上验证其有效性。
摘要：
近年来，开放域对话系统研究吸引了学术界和工业界研究人员的广泛兴趣。开放域对话系统的目标是在对话中模仿人类。此前关于单轮对话生成的工作极大地推动了开放域对话系统的研究。然而，由于人类对话具有连贯性和上下文依赖特性，理解多个单轮对话并不等同于理解多轮对话。因此，在开放域多轮对话生成中，必须对对话历史的上下文语义进行建模，而不能仅依据最后一句话。已有研究验证了层级循环编码器-解码器框架在开放域多轮对话生成中的有效性。然而，使用基于 RNN 的模型对话语进行层级编码以获得对话历史表示，仍然面临梯度消失问题。为解决该问题，本文提出一种基于静态和动态注意力的方法，对对话历史进行建模，进而生成开放域多轮对话回复。在 Ubuntu 和 Opensubtitles 数据集上的实验结果表明，在多种实验设置下，所提出的基于静态和动态注意力的方法在自动评估指标和人工评估指标上均具有有效性。同时，我们还通过实验验证了将静态注意力与动态注意力相结合在开放域多轮对话生成中的性能。
英文摘要：
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history, rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this paper, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.
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。
