Recurrent neural network interaction quality estimation

Pragst, Louisa; Ultes, Stefan; Minker, Wolfgang

doi:http://dx.doi.org/10.1007/978-981-10-2585-3_31

Recurrent neural network interaction quality estimation

Citation

Pragst L, Ultes S, Minker W. Recurrent neural network interaction quality estimation. In: Jokinen K, Wilcock G, editors. Dialogues with social robots: enablements, analyses, and evaluation. Singapore: Springer; 2016. p. 381-93. (LNEE; no. 427). DOI: 10.1007/978-981-10-2585-3_31

Abstract

Getting a good estimation of the Interaction Quality (IQ) of a spoken dialogue helps to increase the user satisfaction as the dialogue strategy may be adapted accordingly. Therefore, some research has already been conducted in order to automatically estimate the Interaction Quality. This paper adds to this by describing how Recurrent Neural Networks may be used to estimate the Interaction Quality for each dialogue turn and by evaluating their performance on this task. Here, we will show that RNNs may outperform non-recurrent neural networks.