Improving Dialogue Act Classification for Spontaneous Arabic Speech and Instant Messages at Utterance Level

TL;DR

This paper presents a hierarchical statistical model for classifying dialogue acts in spontaneous Arabic speech and instant messages, achieving significant improvements in accuracy through SVM-based experiments on Egyptian call-center data.

Contribution

It introduces a multi-classes hierarchical structure for dialogue act recognition in Arabic, leveraging automatically acquired probabilistic discourse knowledge from annotated dialogue corpora.

Findings

Achieved an average F-measure of 0.912 in dialogue act classification.

Improved F-measure by approximately 20% over previous methods.

Validated effectiveness using extensive SVM-based experiments.

Abstract

The ability to model and automatically detect dialogue act is an important step toward understanding spontaneous speech and Instant Messages. However, it has been difficult to infer a dialogue act from a surface utterance because it highly depends on the context of the utterance and speaker linguistic knowledge; especially in Arabic dialects. This paper proposes a statistical dialogue analysis model to recognize utterance's dialogue acts using a multi-classes hierarchical structure. The model can automatically acquire probabilistic discourse knowledge from a dialogue corpus were collected and annotated manually from multi-genre Egyptian call-centers. Extensive experiments were conducted using Support Vector Machines classifier to evaluate the system performance. The results attained in the term of average F-measure scores of 0.912; showed that the proposed approach has moderately improved F-measure by approximately 20%.