New feature weighting approaches for speech-act classification

Abstract

Speech-act classification is essential to generation and understanding of utterances within a natural language dialogue system since the speech-act of an utterance is closely tied to a user intention. The binary feature weighting scheme has mainly been used for speech-act classification because traditional feature weighting schemes such as tf.idf are not effective in speech-act classification due to the short length of utterances. This paper studies two effective feature weighting schemes using the category distributions of features: (1) the first one exploits the entropy of whole category distributions and (2) the second one the log-odds ratio of positive and negative category distributions. As a result, the proposed schemes show significant improvement on SVM and k-NN classifiers in our experiments.