Active Learning of Extractive Reference Summaries for Lecture Speech Summarization

We propose using active learning for tagging extractive reference summary of lecture speech. The training process of feature-based summarization model usually requires a large amount of training data with high-quality reference summaries. Human production of such summaries is tedious, and since inter-labeler agreement is low, very unreliable. Active learning helps assuage this problem by automatically selecting a small amount of unlabeled documents for humans to hand correct. Our method chooses the unlabeled documents according to the similarity score between the document and the comparable resource—PowerPoint slides. After manual correction, the selected documents are returned to the training pool. Summarization results show an increasing learning curve of ROUGE-L F-measure, from 0.44 to 0.514, consistently higher than that of using randomly chosen training samples.