Is this Dialogue Coherent? Learning from Dialogue Acts and Entities
This work addresses the challenge of dialogue coherence modeling for natural language processing applications, but it is incremental as it builds on existing methods with a new dataset.
The authors tackled the problem of modeling human perception of coherence in open-domain dialogues by creating the SWBD-Coh dataset with annotated turn coherence ratings and analyzing how entities and Dialogue Acts affect coherence. They found that models combining both DA and entity information performed best in predicting coherence ratings and response selection.
In this work, we investigate the human perception of coherence in open-domain dialogues. In particular, we address the problem of annotating and modeling the coherence of next-turn candidates while considering the entire history of the dialogue. First, we create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues annotated with turn coherence ratings, where next-turn candidate utterances ratings are provided considering the full dialogue context. Our statistical analysis of the corpus indicates how turn coherence perception is affected by patterns of distribution of entities previously introduced and the Dialogue Acts used. Second, we experiment with different architectures to model entities, Dialogue Acts and their combination and evaluate their performance in predicting human coherence ratings on SWBD-Coh. We find that models combining both DA and entity information yield the best performances both for response selection and turn coherence rating.