Hybrid data-driven models of machine translation

Groves, Declan; Way, Andy

doi:10.1007/s10590-006-9015-5

Cited by 15 publications

(19 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work has shown the EBMT chunks to have higher precision than their SMT counterparts, but they lack sufficient recall when used in isolation (Groves, 2007). We believe that increasing their influence in the translation model may lead to improved translation accuracy.…”

Section: Discussionmentioning

confidence: 84%

See 1 more Smart Citation

MaTrEx

Tinsley

Ozdowska

et al. 2008

Proceedings of the Third Workshop on Statistical Machine Translation - StatMT '08

Self Cite

View full text Add to dashboard Cite

In this paper, we give a description of the machine translation system developed at DCU that was used for our participation in the evaluation campaign of the Third Workshop on Statistical Machine Translation at ACL 2008.We describe the modular design of our datadriven MT system with particular focus on the components used in this participation. We also describe some of the significant modules which were unused in this task.We participated in the EuroParl task for the following translation directions: SpanishEnglish and French-English, in which we employed our hybrid EBMT-SMT architecture to translate. We also participated in the CzechEnglish News and News Commentary tasks which represented a previously untested language pair for our system. We report results on the provided development and test sets.

show abstract

Section: Discussionmentioning

confidence: 84%

“…Groves (2007) has shown previously that combining EBMT and SMT translation models can lead to considerable improvement over the baseline systems from which they are derived. The results achieved here lead us to believe that on such a large scale there may be a more effective way to incorporate the EBMT chunks.…”

Section: Discussionmentioning

confidence: 99%

MaTrEx

Tinsley

Ozdowska

et al. 2008

Proceedings of the Third Workshop on Statistical Machine Translation - StatMT '08

Self Cite

View full text Add to dashboard Cite

show abstract

“…transferbased and Interlingua-based) (Hutchins, 1993& Hutchins, 1994. With the introduction of Artificial Intelligence technology in MT, more recent approaches have been proposed including alignment template approach to Statistical MT (Och & Ney, 2004), Knowledge-based approach (Nirenburg et al, 1992), Human in loop, and Hybrid methods (Groves & Way, 2006).…”

Section: Machine Translationmentioning

confidence: 99%

InterlinguaPlus Machine Translation Approach for Local Languages: Ekegusii and Swahili

Ombui¹,

Wagacha²,

Nganga³

2014

Proceedings of the 2014 Workshop on the Use of Computational Methods in the Study of Endangered Languages

View full text Add to dashboard Cite

This paper elucidates the InterlinguaPlus design and its application in bi-directional text translations between Ekegusii and Kiswahili languages unlike the traditional translation pairs, one-by-one. Therefore, any of the languages can be the source or target language. The first section is an overview of the project, which is followed by a brief review of Machine Translation. The next section discusses the implementation of the system using Carabao's open machine translation framework and the results obtained. So far, the translation results have been plausible particularly for the resource-scarce local languages and clearly affirm morphological similarities inherent in Bantu languages.

show abstract

“…However, we believe that that latest generation of data-driven MT systems demonstrate an increasing convergence of EBMT and SMT (cf. Groves and Way 2005). After a brief survey of recent developments in EMBT and SMT, we describe a new syntax-based SMT approach that draws successfully from both traditions to produce high-quality translations.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, recent work, including Way and Gough (2005) and Groves and Way (2005) has noted and explored the similarities between phrasal SMT and Marker-based EBMT. Yet these phrasal SMT systems only started to exploit the information that had been used for years in EBMT systems.…”

Section: Introductionmentioning

confidence: 99%

Dependency treelet translation: the convergence of statistical and example-based machine-translation?

Quirk

Menezes

2007

Machine Translation

View full text Add to dashboard Cite

We describe a novel approach to MT that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed decoder and reordering model based on the source dependency tree, in combination with conventional SMT models to incorporate the power of phrasal SMT with the linguistic generality available in a parser. We show that this approach significantly outperforms a leading string-based Phrasal SMT decoder and an EBMT system. We present results from two radically different language pairs, and investigate the sensitivity of this approach to parse quality by using two distinct parsers and oracle experiments. We also validate our automated bleu scores with a small human evaluation.

show abstract

Hybrid data-driven models of machine translation

Cited by 15 publications

References 54 publications

MaTrEx

MaTrEx

InterlinguaPlus Machine Translation Approach for Local Languages: Ekegusii and Swahili

Dependency treelet translation: the convergence of statistical and example-based machine-translation?

Contact Info

Product

Resources

About