Using Moses to integrate multiple rule-based machine translation engines into a hybrid system

Eisele, Andreas; Federmann, Christian; Saint-Amand, Hervé; Jellinghaus, Michael; Herrmann, Thomas; Chen, Yu

doi:10.3115/1626394.1626422

Cited by 23 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the two the SMT/NMT approach is probably most generally favoured as witnessed by the many implementations of systems based upon generic SMT engines such as Moses and THOT [Ortiz-Martinez & Casuberta, 2014], and the various NMT platforms developed by Google [Wu, 2016] et al. RBMT continues to contribute not least in the context of hybrid approaches which seek to use the strengths of both RBMT and SMT/NMT approaches [Eisele et al, 2008& Sanchez-Cartagena et al, 2016 but also in scenarios which are closely controlled and the supporting knowledge bases can be closely tailored to that context. State of the art SMT has coalesced around phrase-based systems.…”

Section: Introductionmentioning

confidence: 99%

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

Franken

Guglielmi

Vanhove

et al. 2010

Thyroid

View full text Add to dashboard Cite

AcknowledgementsAsLing wishes to thank and acknowledge the support of the sponsors of TC39: Gold SponsorSilver Sponsor Silver Sponsor Exhibitor Media Sponsoriii Preface For the past 39 years the international conference, Translating and the Computer (TC), has been a unique forum for academics, users, developers and vendors of translation technology tools. It is a distinctive event where translators, interpreters, researchers and business people, from translation companies, international organisations, universities and research labs, as well as freelance professionals, come together to exchange ideas and learn about the latest developments in translation technologies.Over the last two decades various translation tools such as Translation Memory programs presented at previous TC conferences, have revolutionised the work of translators. Regrettably, the same cannot be said for the work of interpreters who have yet to benefit from suitable language technology tools and resources which could assist them in their work.Given this situation, at this year's 39th TC conference we have decided to put an emphasis on the new and emerging language technologies, tools and resources which can support the work of interpreters. The panel 'New Frontiers in Interpreting Technology' features leading experts and practitioners in interpreting and the TC39 programme offers several talks presenting tools for interpreters. We firmly believe that the presentations and discussions on this topic will encourage the development of innovative tools which will revolutionise the work of interpreters in the near future, as has already been the case for translators.This year's conference also features stimulating talks on Translation Technology topics central to TC conferences including but not limited to machine translation, post-editing, CAT tools and terminology. We are confident that you will find that all the presentations and posters, panels and workshops, will provide interesting user perspectives and opportunities, and will lead to inspiring discussions. We trust that these e-proceedings with in-depth coverage of many of the conference contributions, accepted after a competitive reviewing process, will be an important reference resource and stimulus for future work.We are delighted to present our keynote speakers Alex Waibel, a key pioneer of neural translation tools and their use in simultaneous interpretation, and Roberto Navigli, the father of BabelNet, the largest, continuously-updated multilingual encyclopaedic dictionary, doing pioneering work in areas such as multilingual interpretation, mapping of terms and multilingual concept and entity extraction. The work of both is seminal in the development of language processing tools and resources relevant to translation and interpreting technologies.We would like to thank all those who submitted proposals to the conference, all presenters and all the authors who produced full versions of accepted papers for the proceedings. Special thanks go also to all the delegates who have come from so ...

show abstract

Section: Introductionmentioning

confidence: 99%

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

Franken

Guglielmi

Vanhove

et al. 2010

Thyroid

View full text Add to dashboard Cite

show abstract

“…Andreas Eisele, Christian Federmann, Herv´e Saint Amand, Michael Jellinghaus, Teresa Herrmann and Yu Chen developed a hybrid method integrating a rule based with a hierarchical translation system [30]. This method is a statistical and rule based hybrid approach.…”

Section: Word Alignment and Rule Based Approachmentioning

confidence: 99%

“…This method is a statistical and rule based hybrid approach. The hybrid system inherits the lexicons from both sub-systems as well as other merits of each system [30]. The method uses word alignment method and rule based approach to extract phrases.…”

Section: Word Alignment and Rule Based Approachmentioning

confidence: 99%

“…Phrase tables are generated from both statistical method and rule based method. These phrase tables are later combined so that the hybrid system can exploit knowledge from both methods [30]. The advantage is that the hybrid method can gain extra knowledge from rule-based system but the errors in rule-based system can affect the correct information in statistical system [30].…”

Section: Word Alignment and Rule Based Approachmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Phrase Structure Learning Methods for Text Classification

Prasad¹,

Sebastian²

2014

IJNLC

View full text Add to dashboard Cite

Text classification is a task of automatic classification of text into one of the predefined categories. The problem of text classification has been widely studied in different communities like natural language processing, data mining and information retrieval. Text classification is an important constituent in many information management tasks like topic identification, spam filtering, email routing, language identification, genre classification, readability assessment etc. The performance of text classification improves notably when phrase patterns are used. The use of phrase patterns helps in capturing non-local behaviours and thus helps in the improvement of text classification task. Phrase structure extraction is the first step to continue with the phrase pattern identification. In this survey, detailed study of phrase structure learning methods have been carried out. This will enable future work in several NLP tasks, which uses syntactic information from phrase structure like grammar checkers, question answering, information extraction, machine translation, text classification. The paper also provides different levels of classification and detailed comparison of the phrase structure learning methods.

show abstract

“…University of Saarbruecken uses a hybrid system of SMT and RBMT in a multi engine setup. It is a variant of standard SMT technology to align translation from one or more RBMT system with the source text and incorporated phrases extracted from these alignments into the phrase table of the SMT system [24]. It uses Moses to find good combination of phrases from SMT training data with the phrases derived from RBMT.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Translation Shared Task on Statistical Machine Translation: A Comparison of the Systems Output

Rahman¹

2012

IJCA

View full text Add to dashboard Cite

The ACL Workshop on Statistical Machine Translation proposed a translation shared task focused on European language pairs. Participants used their systems to translate into the target language a test set of unseen sentences in the source language. Involved languages were French, English, Spanish, German, Czech and Hungarian. The goal of this work is to quantitatively compare the translations generated by different systems. In particular, a selection of submitted runs for the French-English, German-English and SpanishEnglish tasks were analyzed. The systems involved in our investigation cover all the main approaches to machine translation, that is rule-based, statistical, example-based and hybrid.

show abstract

Using Moses to integrate multiple rule-based machine translation engines into a hybrid system

Cited by 23 publications

References 8 publications

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

A Survey on Phrase Structure Learning Methods for Text Classification

Translation Shared Task on Statistical Machine Translation: A Comparison of the Systems Output

Contact Info

Product

Resources

About

Using Moses to integrate multiple rule-based machine translation engines into a hybrid system

Cited by 23 publications

References 8 publications

Distribution and Dynamics of 99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

Distribution and Dynamics of 99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

A Survey on Phrase Structure Learning Methods for Text Classification

Translation Shared Task on Statistical Machine Translation: A Comparison of the Systems Output

Contact Info

Product

Resources

About

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice

Distribution and Dynamics of ^99mTc-Pertechnetate Uptake in the Thyroid and Other Organs Assessed by Single-Photon Emission Computed Tomography in Living Mice