In the context of natural language processing, representation learning has emerged as a newly active research subject because of its excellent performance in many applications. Learning representations of words is a pioneering study in this school of research. However, paragraph (or sentence and document) embedding learning is more suitable/reasonable for some tasks, such as sentiment classific...

Paragraph-by-paragraph machine translation seems to be for now, an unjustifiably complicated task for practical needs. It involves the complete understanding of the paragraph, the determination of discourse topic(s), goals, intentions, so that the output can be produced in accordance with the respective discourse rules and purposes. However, recognizing topic, goal, intention by a computer prog...

We propose and motivate a novel task: paragraph segmentation. We discuss and compare this task with text segmentation and discourse parsing. We present a system that performs the task with high accuracy. A variety of features is proposed and examined in detail. The best models turn out to include lexical, coherence, and structural features.

Over the years, the amount of information avmlable electromcally has grown mamfold There Is an increasing demand for automatic methods for text summarization Dommnindependent techniques for automauc summanzation by paragraph extractton have been proposed m (Salton et al , 1994, Salton et al , 1996b) In tins study, we attempt to evainate these methods by companng the automatlcally generated extr...