Automatic dialogue acts classification in Slovak dialogues

Abstract

Dialogue acts classification plays an important role in advanced dialogue management systems. They represent intention of the dialogue participant in the particular part of the dialogue interaction. Dialogue act classification lies in the classification of the spoken utterances according to their discourse function. It relies mainly on the classical machine learning techniques similar as in case of natural language processing (NLP) tasks. The HMM-based approach was applied to perform DA classification of utterances in Slovak language. Episodes of the Slovak TV talk show were used for creating of dialogue corpus with DA labels. New simplified annotation schema was designed and used for labeling the corpus with 12 DA classes. Bigram models of DA classes and dialogue grammar were trained on training part of the corpus. Decoding of testing utterances was done by comparing probabilities of occurrence and perplexity over trained bigrams. Obtained results are comparable with similar techniques and data sets.