Discourse Processing

摘要: Discourse Processing here is framed as marking up a text with structural descriptions on several levels, which can serve to support many language-processing or text-mining tasks. We first explore some ways of assigning structure the document level: logical determined by layout text, its genre-specific content structure, and breakdown into topical segments. Then focus moves phenomena local coherence. introduce problem coreference look at methods for building chains coreferring entities in text. Next, notion coherence relation introduced second important factor study role connectives other means signaling such relations then return level larger textual units, where tree graph structures be ascribed recursively relations. Taken together, these inform summarization, information extraction, discourse-aware sentiment analysis, question answering, like.