Automatic Chinese dialog acts recognition with multiple kernel learning

Dialogue acts recognition is a significant step in many human-machine dialogue systems as dialogue acts can describe the human intention to some extent. However, conventional classifiers get poor performance when applied to this task due to the multiple modal features. For a Chinese dialogue acts recognition task in the CASIA-CASSIL corpus, ten kinds of features can be extracted. Different kinds of features have different dimensions and stay in different feature space, it seems unreasonable to concatenate these features to a long vector and then deliver this feature vector to a classifier. To address this issue, we investigate into the multiple kernel learning method. This method uses the kernel trick to map the original features into a unified Hilbert space and then combine them. To show the effectiveness, we compare it with several baseline methods. Results of the experiments demonstrate that the multiple kernel learning method performs much better than all the baseline methods.