Co-training using prosodic and lexical information for sentence segmentation

We investigate the application of the co-training learning algorithm on the sentence boundary classification problem by using lexical and prosodic information. Co-training is a semisupervised machine learning algorithm that uses multiple weak classifiers with a relatively small amount of labeled data and incrementally uses unlabeled data. The assumption in cotraining is that the classifiers can co-train each other, as one can label samples that are difficult for the other. The sentence segmentation problem is very appropriate for the co-training method since it satisfies the main requirements of the cotraining algorithm: the dataset can be described by two disjoint and natural views that are redundantly sufficient. In our case, the feature sets are capturing lexical and prosodic information. The experimental results on the ICSI Meeting (MRDA) corpus show the effectiveness of the co-training algorithm for this task.