Exploring Effective Information Utilization in Multi-Turn Topic-Driven Conversations
This work addresses a specific bottleneck in dialogue generation for Chinese news-based conversations, representing an incremental improvement.
The paper tackled the challenge of fusing dialogue history and topic information in multi-turn conversations within the input length limits of pre-trained language models, achieving competitive performance on the NaturalConv dataset by using Fusion-in-Decoder with specific channel settings.
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.