Please use this identifier to cite or link to this item:
Title: Discourse parsing: Inferring discourse structure, modeling coherence, and its applications
Keywords: discourse parsing, discourse structure, text coherence, text summarization, argumentative zoning
Issue Date: 5-Jan-2012
Citation: LIN ZIHENG (2012-01-05). Discourse parsing: Inferring discourse structure, modeling coherence, and its applications. ScholarBank@NUS Repository.
Abstract: In this thesis, we investigate a natural language problem of parsing a free text into its discourse structure. We first propose a classifier to tackle this with the use of contextual features, word-pairs, and constituent and dependency parse features. We then design a parsing algorithm and implement it into a full parser in a pipeline. We present a comprehensive evaluation on the parser from both component-wise and error-cascading perspectives. Textual coherence is strongly connected to a text's discourse structure. We present a novel model to represent and assess the discourse coherence of a text with the use of our discourse parser. We implement this model and apply it towards the text ordering ranking task, which aims to discern an original text from a permuted ordering of its sentences. We demonstrate that incorporating discourse features can significantly improve two NLP tasks -- argumentative zoning and summarization -- in the scholarly domain.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LinZ.pdf850.28 kBAdobe PDF



Page view(s)

checked on May 17, 2019


checked on May 17, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.