Multimodal Dialogue State Tracking

Hung Le, Nancy F. Chen, Steven Hoi

Keywords: dialogue state tracking, multimodal, video-grounded dialogue, video-dialogue transformer network, synthetic benchmark

Abstract: Designed for tracking user goals in dialogues, a dialogue state tracker is an essential component in a dialogue system. However, the research of dialogue state tracking has largely been limited to unimodality, in which slots and slot values are limited by knowledge domains (e.g. restaurant domain with slots of restaurant name and price range) and are defined by specific database schema. In this paper, we propose to extend the definition of dialogue state tracking to multimodality. Specifically, we introduce a novel dialogue state tracking task to track the information of visual objects that are mentioned in video-grounded dialogues. Each new dialogue utterance may introduce a new video segment, new visual objects, or new object attributes and a state tracker is required to update these information slots accordingly. Secondly, to facilitate research of this task, we developed DVD-DST, a synthetic video-grounded dialogue benchmark with annotations of multimodal dialogue states. Thirdly, we designed a novel baseline, Video-Dialogue Transformer Network (VDTN), for this task. VDTN combines both object-level features and segment-level features and learns contextual dependencies between videos and dialogues to generate multimodal dialogue states. We optimized VDTN for a state generation task as well as a self-supervised video understanding task which recovers video segment or object representations. Finally, we trained VDTN to use the decoded states in a response prediction task. Together with comprehensive ablation and qualitative analysis, we discovered interesting insights towards building more capable multimodal dialogue systems.

One-sentence Summary: we introduced a novel Multimodal Dialogue State Tracking task that tracks visual objects mentioned in dialogue context from turn to turn. We proposed a strong Video-Dialogue Transformer Network baseline and compared with unimodal DST approaches.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.07898/code)