THESIS TITLE: ADVANCES IN PUNCTUATION AND DISFLUENCY PREDICTION

Abstract

This thesis improves state-of-the-art natural language processing (NLP) techniques in automatic punctuation and disfluency prediction. It can be applied to post-process automatically recognized speech output for downstream NLP tasks. For punctuation prediction, we propose using dynamic conditional random fields for joint sentence boundary and punctuation prediction. We have also investigated several model optimization techniques which are important for practical applications. For disfluency prediction, we propose a beam-search decoder approach. Our decoder can combine generative models like n-gram language models (LM) and discriminative models like Max-margin Markov Networks (M3N). Lastly, we have performed an empirical study on various state-of-the-art methods for combining the two tasks, and we have highlighted some insights in balancing the trade-off between performance and efficiency for building practical systems.