Common Ground Tracking in Multimodal Dialogue

arXiv:2403.17284v1 Announce Type: new
Abstract: Within Dialogue Modeling research in AI and NLP, considerable attention has been spent on ``dialogue state tracking'' (DST), which is the ability to update the representations of the speaker's needs at each turn in the dialogue by taking into account the past dialogue moves and history. Less studied but just as important to dialogue modeling, however, is ``common ground tracking'' (CGT), which identifies the shared belief space held by all of the participants in a …

abstract arxiv attention cs.cl dialogue history modeling multimodal nlp research speaker state tracking type update