The contribution of mutual information in the intonational phrase prediction in chinese text

The contribution of Mutual Information (MI) in the Intonational Phrase (IP) prediction is analyzed and Verified in this paper. The basic idea of employing MI in IP prediction is that people is likely to pause between the less correlated words, where the MI value is low. The paper presents a decision tree based predictor which adopts POS as the main feature firstly as the baseline, and then the paper analyzes the correlation between MI and IP. The approach which only bases oil the MI to predict the IP boundary is demonstrated ill this paper, and three methods combining the MI and POS in the predictor is presented too. In the MI based approach, a considerable performance (F-Score: 64.2%) is achieved, and 3.4% promotion from the baseline is achieved after combining MI and POS in our experiment. All our work indicates that MI is all effective feature in the prosodic phrase boundaries prediction in Chinese text, and combining the MI and POS in the predictor is valuable.