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

A memory-based classification approach to marker-based EBMT

van den Bosch, Antal and Stroppa, Nicolas and Way, Andy (2007) A memory-based classification approach to marker-based EBMT. In: METIS-II Workshop on New Approaches to Machine Translation, 11 January 2007, Leuven, Belgium.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
250Kb

Abstract

We describe a novel approach to example-based machine translation that makes use of marker-based chunks, in which the decoder is a memory-based classifier. The classifier is trained to map trigrams of source-language chunks onto trigrams of target-language chunks; then, in a second decoding step, the predicted trigrams are rearranged according to their overlap. We present the first results of this method on a Dutch-to-English translation system using Europarl data. Sparseness of the class space causes the results to lag behind a baseline phrase-based SMT system. In a further comparison, we also apply the method to a word-aligned version of the same data, and report a smaller difference with a word-based SMT system. We explore the scaling abilities of the memory-based approach, and observe linear scaling behavior in training and classification speed and memory costs, and loglinear BLEU improvements in the amount of training examples.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:example-based machine translation;
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Official URL:http://www.mt-archive.info/METIS-2007-TOC.htm
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland, SFI 05/IN/1732
ID Code:15267
Deposited On:09 Mar 2010 16:56 by DORAS Administrator. Last Modified 27 Apr 2010 15:13

Download statistics

Archive Staff Only: edit this record