Long-range context modeling is crucial to both dialogue understanding and generation. The most popular method for dialogue context representation is to concatenate the last-$k$ previous utterances. However, this method may not be ideal for conversations containing long-range dependencies as it cannot look beyond last-$k$ utterances. In this work, we propose DialoGen, a novel encoder-decoder based framework for conversational response generation with a generalized context representation that can look beyond the last-$k$ utterances. Hence the method is adaptive to conversations with long-range dependencies. The main idea of our approach is to identify and utilize the most relevant historical utterances instead of the last-$k$ utterances in chronological order. We study the effectiveness of our proposed method on both dialogue generation (open-domain) and understanding (DST) tasks. DialoGen achieves comparable performance with the state-of-the-art models on DailyDialog dataset. We also observe performance gain in existing DST models with our proposed context representation strategy on MultiWOZ dataset. We discuss the generalizability and interpretability of DialoGen and show that the relevance score of previous utterances agrees well with human cognition.

翻译：长程上下文建模对对话理解与生成至关重要。当前最流行的对话上下文表征方法是将最近$k$个历史语句进行拼接。然而，该方法无法关注最近$k$条语句以外的信息，因此对于包含长程依赖的对话而言并非理想选择。本文提出DialoGen——一种基于编码器-解码器的对话响应生成框架，该框架采用能够超越最近$k$条语句的泛化上下文表征，从而自适应处理具有长程依赖的对话。其核心思想在于识别并利用最具相关性的历史语句，而非按时间顺序机械选取最近$k$条。我们在对话生成（开放域）与理解（对话状态追踪）任务上验证了该方法的效果。在DailyDialog数据集上，DialoGen取得了与最先进模型可比拟的性能；同时，在MultiWOZ数据集上，我们提出的上下文表征策略显著提升了现有对话状态追踪模型的性能。本文进一步探讨了DialoGen的泛化性与可解释性，证明历史语句相关性得分与人类认知高度吻合。