"Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking
This is an incremental review paper summarizing recent research for the dialogue systems community.
The paper surveys recent advances in dialogue state tracking (DST), highlighting the emergence of text-to-text approaches as dominant and noting that while neural methods have driven progress, issues like generalizability remain underexplored.
While communicating with a user, a task-oriented dialogue system has to track the user's needs at each turn according to the conversation history. This process called dialogue state tracking (DST) is crucial because it directly informs the downstream dialogue policy. DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach. In this review paper, we first present the task and its associated datasets. Then, considering a large number of recent publications, we identify highlights and advances of research in 2021-2022. Although neural approaches have enabled significant progress, we argue that some critical aspects of dialogue systems such as generalizability are still underexplored. To motivate future studies, we propose several research avenues.