Paper: Detecting Problematic Turns In Human-Machine Interactions: Rule-Induction Versus Memory-Based Learning Approaches

ACL ID P01-1012
Title Detecting Problematic Turns In Human-Machine Interactions: Rule-Induction Versus Memory-Based Learning Approaches
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2001
Authors
  • Antal van den Bosch (Tilburg University, Tilburg The Netherlands)
  • Emiel Krahmer (Eindhoven University of Technology, Eindhoven The Netherlands; Tilburg University, Tilburg The Netherlands)
  • Marc Swerts (Eindhoven University of Technology, Eindhoven The Netherlands; University of Antwerp, Antwerp Belgium)

We address the issue of on-line detec- tion of communication problems in spoken dialogue systems. The useful- ness is investigated of the sequence of system question types and the word graphs corresponding to the respective user utterances. By applying both rule- induction and memory-based learning techniques to data obtained with a Dutch train time-table information system, the current paper demonstrates that the aforementioned features indeed lead to a method for problem detec- tion that performs significantly above baseline. The results are interesting from a dialogue perspective since they employ features that are present in the majority of spoken dialogue systems and can be obtained with little or no computational overhead. The results are interesting from a machine learning perspecti...