INTERSPEECH 2007
8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Classification of Discourse Functions of Affirmative Words in Spoken Dialogue

Agustín Gravano (1), Stefan Benus (2), Julia Hirschberg (1), Shira Mitchell (3), Ilia Vovsha (1)

(1) Columbia University, USA
(2) Brown University, USA
(3) Harvard University, USA

We present results of a series of machine learning experiments that address the classification of the discourse function of single affirmative cue words such as alright, okay and mm-hm in a spoken dialogue corpus. We suggest that a simple discourse/sentential distinction is not sufficient for such words and propose two additional classification sub-tasks: identifying (a) whether such words convey acknowledgment or agreement, and (b) whether they cue the beginning or end of a discourse segment. We also study the classification of each individual word into its most common discourse functions. We show that models based on contextual features extracted from the time-aligned transcripts approach the error rate of trained human aligners.

Full Paper

Bibliographic reference.  Gravano, Agustín / Benus, Stefan / Hirschberg, Julia / Mitchell, Shira / Vovsha, Ilia (2007): "Classification of discourse functions of affirmative words in spoken dialogue", In INTERSPEECH-2007, 1613-1616.