Please use this identifier to cite or link to this item:
Title: A Text Rewriting Decoder with Application to Machine Translation
Keywords: machine translation, text rewriting, beam search, social media text normalization, source language adaptation, resource-poor machine translation
Issue Date: 20-Aug-2013
Citation: WANG PIDONG (2013-08-20). A Text Rewriting Decoder with Application to Machine Translation. ScholarBank@NUS Repository.
Abstract: The main aim of this thesis is to propose a text rewriting decoder, and then apply it to two applications: social media text normalization for machine translation, and source language adaptation for resource-poor machine translation. We propose a text rewriting decoder based on beam search which can be used to rewrite texts from one form to another. In contrast to the beam-search decoders widely used in statistical machine translation (SMT) and automatic speech recognition (ASR), the text rewriting decoder works on the sentence level, so it can use sentence-level features. We then apply the decoder to social media text normalization for both Chinese and English to improve machine translation. Finally, the decoder is used to improve machine translation from a resource-poor language to a target language by adapting a large bi-text for a related resource-rich language and the same target language.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
WangPD.pdf648.27 kBAdobe PDF



Google ScholarTM


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