Combining Task and Dialogue Streams in Unsupervised Dialogue Act Models
Aysu Ezen-Can, Kristy Elizabeth Boyer · 2014
Unsupervised machine learning ap-proaches hold great promise for recog-nizing dialogue acts, but the performance of these models tends to be much lower than the accuracies reached by supervised models. However, some dialogues, such as task-oriented dialogues with parallel task streams, hold rich information that has not yet been leveraged within unsu-pervised dialogue act models. This paper investigates incorporating task features into an unsupervised dialogue act model trained on a corpus of human tutoring in introductory computer science. Exper-imental results show that incorporating task features and dialogue history fea-tures significantly improve unsupervised dialogue act classification, particularly within a hierarchical framework that gives prominence to dialogue history. This work constitutes a step toward building high-performing unsupervised dialogue act models that will be used in the next generation of task-oriented dialogue systems.