Conversations are always related to certain topics. However, it is challenging to fuse dialogue history and topic information from various sources at the same time in current dialogue generation models because of the input length limit of pre-trained language models (PLMs). In order to expand the information that PLMs can utilize, we encode topic and dialogue history information using certain prompts with multiple channels of Fusion-in-Decoder (FiD) and explore the influence of three different channel settings. In this paper, our experiments focus on a specific Chinese dataset named NaturalConv, where the conversation revolves around a piece of recent news. We thoroughly compared different dialogue models and different FiD channel settings. Empirical results show that by combining our proposed whole passage channel with additional history channel, our methods can achieve competitive performance on NaturalConv, making it possible to encode various information from excessively long texts.
翻译:对话总是与某些专题相关,然而,由于培训前语言模式(PLMs)的输入长度限制,在目前的对话生成模式中,将对话历史和不同来源的专题信息同时结合到不同的对话模式中,这具有挑战性。为了扩大PLMs能够使用的信息,我们用多种融合-解说(Fid)渠道的某些提示来编码专题和对话历史信息,并探索三种不同频道环境的影响。在本文中,我们的实验侧重于一个名为“自然Conv”的中国特定数据集,在那里,对话围绕一条最新新闻进行。我们彻底比较了不同的对话模式和不同的FiD频道设置。“经验”结果表明,通过将我们提议的整个通道与更多的历史频道结合起来,我们的方法可以在自然Conus上实现竞争性表现,从而有可能将来自过长文本的各种信息编码。