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

Hybridity in MT: experiments on the Europarl corpus

Groves, Declan and Way, Andy (2006) Hybridity in MT: experiments on the Europarl corpus. In: EAMT 2006 - 11th Annual conference of the European Association for Machine Translation, 19-20 June 2006, Oslo, Norway.

Full text available as:

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


(Way & Gough, 2005) demonstrate that their Marker-based EBMT system is capable of outperforming a word-based SMT system trained on reasonably large data sets. (Groves & Way, 2005) take this a stage further and demonstrate that while the EBMT system also outperforms a phrase-based SMT (PBSMT) system, a hybrid 'example-based SMT' system incorporating marker chunks and SMT sub-sentential alignments is capable of outperforming both baseline translation models for French{English translation. In this paper, we show that similar gains are to be had from constructing a hybrid 'statistical EBMT' system capable of outperforming the baseline system of (Way & Gough, 2005). Using the Europarl (Koehn, 2005) training and test sets we show that this time around, although all 'hybrid' variants of the EBMT system fall short of the quality achieved by the baseline PBSMT system, merging elements of the marker-based and SMT data, as in (Groves & Way, 2005), to create a hybrid 'example-based SMT' system, outperforms the baseline SMT and EBMT systems from which it is derived. Furthermore, we provide further evidence in favour of hybrid systems by adding an SMT target language model to all EBMT system variants and demonstrate that this too has a positive e®ect on translation quality.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
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:
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:15277
Deposited On:10 Mar 2010 16:15 by DORAS Administrator. Last Modified 20 Feb 2017 13:46

Download statistics

Archive Staff Only: edit this record