Joint Modeling of Content and Discourse Relations in Dialogues
This work addresses the challenge of analyzing complex dialogues for applications like meeting summarization or team coordination, though it appears incremental as it builds on existing models.
The authors tackled the problem of identifying salient discussion points and labeling discourse relations in spoken meetings, achieving state-of-the-art performance on content selection and discourse relation prediction tasks across two meeting corpora, and also improved predictive performance for team consistency understanding.
We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse relations are treated as latent variables. Experimental results on two popular meeting corpora show that our joint model can outperform state-of-the-art approaches for both phrase-based content selection and discourse relation prediction tasks. We also evaluate our model on predicting the consistency among team members' understanding of their group decisions. Classifiers trained with features constructed from our model achieve significant better predictive performance than the state-of-the-art.