Paper: Discovering Latent Structure in Task-Oriented Dialogues

ACL ID P14-1004
Title Discovering Latent Structure in Task-Oriented Dialogues
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

A key challenge for computational conver- sation models is to discover latent struc- ture in task-oriented dialogue, since it pro- vides a basis for analysing, evaluating, and building conversational systems. We pro- pose three new unsupervised models to discover latent structures in task-oriented dialogues. Our methods synthesize hidden Markov models (for underlying state) and topic models (to connect words to states). We apply them to two real, non-trivial datasets: human-computer spoken dia- logues in bus query service, and human- human text-based chats from a live tech- nical support service. We show that our models extract meaningful state represen- tations and dialogue structures consistent with human annotations. Quantitatively, we show our models achieve superior per- formance on h...