Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Low-resource machine translation using MATREX: The DCU machine translation system for IWSLT 2009

Ma, Yanjun and Okita , Tsuyoshi and Cetinoglu, Ozlem and Du, Jinhua and Way, Andy (2009) Low-resource machine translation using MATREX: The DCU machine translation system for IWSLT 2009. In: the IWSLT 2009 Workshop (IWSLT 2009) , 1-2 Dec. 2009, Tokyo, Japan.

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


In this paper, we give a description of the Machine Translation (MT) system developed at DCU that was used for our fourth participation in the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT 2009). Two techniques are deployed in our system in order to improve the translation quality in a low-resource scenario. The first technique is to use multiple segmentations in MT training and to utilise word lattices in decoding stage. The second technique is used to select the optimal training data that can be used to build MT systems. In this year’s participation, we use three different prototype SMT systems, and the output from each system are combined using standard system combination method. Our system is the top system for Chinese–English CHALLENGE task in terms of BLEU score.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Uncontrolled Keywords:word lattices; MATREX
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:16162
Deposited On:20 Jun 2011 14:14 by Shane Harper. Last Modified 27 Feb 2017 14:24

Download statistics

Archive Staff Only: edit this record