NewsDialogues: Towards Proactive News Grounded Conversation
This addresses the lack of data and task definition for news-based dialogue systems, which is incremental as it builds on existing conversation tasks.
The authors tackled the problem of news grounded conversation by proposing a new task, Proactive News Grounded Conversation, and collected a Chinese dataset with 1K conversations and 14.6K utterances, achieving effectiveness through their Predict-Generate-Rank method.
Hot news is one of the most popular topics in daily conversations. However, news grounded conversation has long been stymied by the lack of well-designed task definition and scarce data. In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news. In addition, both information-seeking and chit-chat scenarios are included realistically, where the user may ask a series of questions about the news details or express their opinions and be eager to chat. To further develop this novel task, we collect a human-to-human Chinese dialogue dataset \ts{NewsDialogues}, which includes 1K conversations with a total of 14.6K utterances and detailed annotations for target topics and knowledge spans. Furthermore, we propose a method named Predict-Generate-Rank, consisting of a generator for grounded knowledge prediction and response generation, and a ranker for the ranking of multiple responses to alleviate the exposure bias. We conduct comprehensive experiments to demonstrate the effectiveness of the proposed method and further present several key findings and challenges to prompt future research.