Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Treating dialogue quality evaluation as an anomaly detection problem

: Nedelchev, R.; Lehmann, J.; Usbeck, R.

Volltext ()

Calzolari, N. ; European Language Resources Association -ELRA-, Paris:
12th Language Resources and Evaluation Conference, LREC 2020. Proceedings. Online resource : May 11-16, 2020, Palais du Pharo, Marseille, France : conference proceedings
Paris: ELRA, 2020
ISBN: 979-10-95546-34-4
Language Resources and Evaluation Conference (LREC) <12, 2020, Marseille/cancelled>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()

Dialogue systems for interaction with humans have been enjoying increased popularity in the research and industry fields. To this day, the best way to estimate their success is through means of human evaluation and not automated approaches, despite the abundance of work done in the field. In this paper, we investigate the effectiveness of perceiving dialogue evaluation as an anomaly detection task. The paper looks into four dialogue modeling approaches and how their objective functions correlate with human annotation scores. A high-level perspective exhibits negative results. However, a more in-depth look shows limited potential for using anomaly detection for evaluating dialogues.