Automatic Annotation of Dialogue Structure from Simple User Interaction

Abstract. In [1], we presented a method for automatic detection of action items from natural conversation. This method relies on supervised classification techniques that are trained on data annotated according to a hierarchical notion of dialogue structure; data which are expensive and time-consuming to produce. In [2], we presented a meeting browser which allows users to view a set of automatically-produced action item summaries and give feedback on their accuracy. In this paper, we investigate methods of using this kind of feedback as implicit supervision, in order to bypass the costly annotation process and enable machine learning through use. We investigate, through the transformation of human annotations into hypothetical idealized user interactions, the relative utility of various modes of user interaction as well as various techniques for automatically producing training instances from interaction. We show that performance improvements are possible from interaction alone, even...

• Type: Conference
• Year: 2007
• Where: MLMI
• Authors: Matthew Purver, John Niekrasz, Patrick Ehlen
• Keywords: Action Item, Machine Learning, MLMI 2007, Supervised Classification Techniques, User Interaction