Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Background of Metis-II Implementations
German Source-Language Analysis
German: Statistical N-Gram Language Modelling
German SL Analysis
SL vs. TL Information for Word Order Hypotheses
Results Metis-II vs. Systran
Conclusions from Statistical Language Modelling
Conclusions
References
All Topics
Psychology
Cognitive Science

METIS-II: low resource machine translation

Profile image of Olga YannoutsouOlga Yannoutsou

2008, Machine Translation

Abstract

METIS-II was a EU-FET MT project running from October 2004 to September 2007, which aimed at translating free text input without resorting to parallel corpora. The idea was to use 'basic' linguistic tools and representations and to link them with patterns and statistics from the monolingual target-language corpus. The METIS-II project has four partners, translating from their 'home' languages Greek, Dutch, German, and Spanish into English. The paper outlines the basic ideas of the project, their implementation, the resources used, and the results obtained. It also gives examples of how METIS-II has continued beyond its lifetime and the original scope of the project. On the basis of the results and experiences obtained, we believe that the approach is promising and offers the potential for development in various directions.

Related papers

Proceedings of the Sixth Workshop on Statistical Machine Translation}
Joel Tetreault

Proceedings of the Sixth Workshop on Statistical Machine Translation}

The focus of our workshop was to use parallel corpora for machine translation. Recent experimentation has shown that the performance of SMT systems varies greatly with the source language. In this workshop we encouraged researchers to investigate ways to improve the performance of SMT systems for diverse languages, including morphologically more complex languages, languages with partial free word order, and low-resource languages.

View PDFchevron_right
Introduction to the Special Issue on Machine Translation for Low-Resource Languages
Jonathan Washington

Machine Translation, 2020

View PDFchevron_right
EU-BRIDGE MT: Combined Machine Translation
Maria Nadejde, Teresa Herrmann

Proceedings of the Ninth Workshop on Statistical Machine Translation, 2014

This paper describes one of the collaborative efforts within EU-BRIDGE to further advance the state of the art in machine translation between two European language pairs, German→English and English→German. Three research institutes involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the shared translation task of the evaluation campaign at the ACL 2014 Eighth Workshop on Statistical Machine Translation (WMT 2014).

View PDFchevron_right

References (52)

  1. Abdelali, A., J. Cowie, S. Helmreich, W. Jin, M. P. Milagros, B. Ogden, H. M. Rad, and R. Zacharski: 2006, ' Guarani: a case study in resource development for quick ramp-up MT'. In: Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, "Visions for the Future of Machine Translation". Cambridge, Massa-chusetts, USA, pp. 1-9.
  2. Alegria, I., A. D. de Ilarraza, G. Labaka, M. Lersundi, A. Mayor, K. Sarasola, M. L. Forcada, S. Ortiz-Rojas, and L. Padró: 2005, ' An open architecture for transfer- based machine translation between Spanish and Basque'. In: Proceedings of the X Machine Translation Summit workshop OSMaTran: Open-Source Machine Translation X. Phuket, Thailand, pp. 7-14.
  3. Alsina, A., T. Badia, G. Boleda, S. Bott, A. Gil, M. Quixal, and O. Valentí: 2002, 'CATCG: a general purpose parsing tool applied'. In: Proceedings of Third International Conference on Language Resources and Evaluation. Las Palmas, Spain, pp. 1130-1134.
  4. Anastasiou, D. and O. Culo: 2007, 'Using Topological Information for detecting idiomatic verb phrases in German'. In: Proceedings of the Conference on Practical Applications in Language and Computers (PALC). Lodz, Poland, pp. 49-58.
  5. Badia, T., G. Boleda, M. Melero, and A. Oliver: 2005, 'An n-gram approach to exploiting a monolingual corpus for machine translation'. In: MT Summit X Workshop on Example-Based Machine Translation. Pukhet, Thailand, pp. 1-7.
  6. Badia, T., M. Melero, and O. Valentín: 2008, 'Rapid Deployment of a New METIS Language Pair: Catalan-English'. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC08). Marrakech, Morocco, p. 96.
  7. Boutsis, S., P. Prokopidis, V. Giouli, and S. Piperidis: 2000, 'A Robust Parser for Unrestricted Greek Text'. In: Proceedings of the 2 nd International Conference on Language Resources and Evaluation (LREC). Athens, Greece, pp. 467-482.
  8. Brants, T.: 2000, 'TnT -a statistical part-of-speech tagger'. In: Proceedings of the 6th Applied Natural Language Processing Conference (ANLP). Seattle, Washington, USA, pp. 224-231.
  9. Brown, R. and R. Frederking: 1995, 'Applying statistical English language modelling to symbolic machine translation'. In: Proceedings of the 6th International Con- ference on Theoretical and Methodological Issues in Machine Translation (TMI). Leuven, Belgium, pp. 221-239.
  10. Carl, M.: 2007, 'METIS-II: The German to English MT System'. In: Proceedings of the 11th Machine Translation Summit. Copenhagen, Denmark, pp. 65-72.
  11. Carl, M.: 2008, 'Using Log-linear Models for Tuning Machine Translation Output'. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC08). Marrakech, Morocco, p. 49.
  12. Carl, M. and E. Rascu: 2006, 'A Dictionary Lookup Strategy for Translating Dis- continuous Phrases'. In: Proceedings of the European Association for Machine Translation. Oslo, Norway, pp. 49-58.
  13. Carl, M., P. Schmidt, and J. Schütz: 2005, 'Reversible Template-based Shake & Bake Generation'. In: Proceedings of the Example-Based Machine Translation Workshop held in conjunction with Machine Translation Summit X. Phuket, Thailand, pp. 17-26.
  14. Carpuat, M. and D. Wu: 2007, 'How Phrase Sense Disambiguation outperforms Word Sense Disambiguation for Statistical Machine Translation'. In: Proceedings of the 11 th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-07). Skövde, Sweden, pp. 43-52.
  15. Doddington, G.: 2002, 'Automatic Evaluation of Machine Translation Quality using N-gram Co-occurrence Statistics'. In: Proceedings of the second Human Language Technologies Conference (HLT-02). San Diego, pp. 128-132.
  16. Dologlou, I., S. Markantonatou, G. Tambouratzis, O. Yannoutsou, A. Fourla, and N. Ioannou: 2003, 'Using Monolingual Corpora for Statistical Machine Translation'. In: Proceedings of EAMT/CLAW 2003. Dublin, Ireland, pp. 61-68.
  17. EAGLES: 1994, 'Guidelines, EAG-LWG-T4-2'. Technical report, ILC-CNR, Pisa, Italy.
  18. Engelbrecht, H. and T. Schultz: 2005, 'Rapid development of an Afrikaans English speech-to-speech translator'. In: International Workshop on Spoken Language Translation: Evaluation Campaign on Spoken Language Translation. Pittsburgh, PA, US., pp. 24-25.
  19. Germann, U., M. Jahr, K. Knight, D. Marcu, and K. Yamada: 2001, 'Fast Decoding and Optimal Decoding for Machine Translation'. In: Proceedings of the 39th ACL and 10th Conference of the European Chapter. Toulouse, France, pp. 228-235.
  20. Gispert, A. and J. B. Mariño: 2006, 'Catalan-English statistical machine transla- tion without parallel corpus: bridging through Spanish'. In: Fifth International Conference on Language Resources and Evaluation (LREC), 5th SALTMIL Workshop on Minority Languages: "Strategies for developing machine translation for minority languages". Genoa, Italy, pp. 65-68.
  21. Habash, N.: 2004, 'The use of a structural n-gram language model in generation- heavy hybrid machine translation'. In: Proceeding 3rd International Conference on Natural Language Generation (INLG '04), volume 3123 of LNAI, Springer, Germany. Brockenhurst, UK, pp. 61-69.
  22. Karlsson, F. e. a.: 1995, Constraint Grammar: A Language-Independent Formalism for Parsing Unrestricted Text. Berlin/New York: Mouton de Gruyter.
  23. Koehn, P.: 2004, 'Pharaoh: a Beam Search Decoder for Phrase-Based Statistical Machine Translation Models'. In: Proceedings of AMTA, the Association for Machine Translation in the Americas. Washington, DC, USA., pp. 115-124.
  24. Koehn, P.: 2005, 'Europarl: A Parallel Corpus for Statistical Machine Translation'. In: Proceedings of MT Summit X. Pukhet, Thailand, pp. 79-86.
  25. Kuhn, H. W.: 1955, 'The Hungarian Method for the assignment problem'. Naval Research Logistics Quarterly 2, 88-97.
  26. Labropoulou, P., E. Mantzari, and M. Gavrilidou: 1996, 'Lexicon -Morphosyntac- tic Specifications: Language-Specific Instantiation (Greek)'. In: PP-PAROLE, MLAP report. Athens, Greece, pp. 63-386.
  27. Langkilde, I. and K. Knight: 1998, 'The Practical Value of n-grams in generation'. In: In Proceedings of the 9th International Natural Language Workshop (INLG '98). Niagara-on-the-Lake, Ontario, pp. 248-255.
  28. Lavie, A., E. Peterson, K. Probst, S. Wintner, and Y. Eytani: 2004, 'Rapid proto- typing of a transfer-based Hebrew-to-English machine translation system'. In: Proceedings of the Tenth Conference on Theoretical and Methodological Issues in Machine Translation. Baltimore, USA, pp. 1-10.
  29. Maas, H.-D.: 1996, 'MPRO -Ein System zur Analyse und Synthese deutscher Wörter'. In: R. Hausser (ed.): Linguistische Verifikation, Sprache und Infor- mation. Tübingen: Max Niemeyer Verlag.
  30. Majithia, H., P. Rennart, and E. Tzoukermann: 2005, 'Rapid ramp-up for statistical machine translation: minimal training for maximal coverage '. In: Proceedings of the Machine Translation Summit X. Phuket, Thailand, pp. 438-444.
  31. Markantonatou, S., S. Sofianopoulos, V. Spilioti, G. Tambouratzis, M. Vassiliou, and O. Yannoutsou: 2006, 'Using Patterns for Machine Translation (MT)'. In: Proceedings of the European Association for Machine Translation 2006. Oslo, Norway, pp. 239-246.
  32. Melero, M., A. Oliver, T. Badia, and T. Suñol: 2007, 'Dealing with Bilingual Di- vergences in MT using Target language N-gram Models'. In: Proceedings of the METIS-II Workshop: New Approaches to Machine Translation, CLIN 17 - Computational Linguistics in the Netherlands. Leuven, Belgium, pp. 19-26.
  33. METIS-II: 2006, 'Validation/Evaluation framework'. Public Report, D5.1, European Commission, FP6-IST-003768, Brussels. http://www.ilsp.gr/metis2/files/ Metis2_D5.1.pdf [25.Aug.2008].
  34. METIS-II: 2007, 'Validation & Fine-Tuning Results for the first Prototype'. Public Report, D5.2, European Commission, FP6-IST-003768, Brussels. http://www. ilsp.gr/metis2/files/Metis2_D5.2.pdf [25.Aug.2008].
  35. Müller, F. H.: 2004, 'Stylebook for the Tübingen Partially Parsed Corpus of Writ- ten German (T ÜPP-D/Z)'. http://www.sfb441.uni-tuebingen.de/a1/pub. html[25.Aug.2008].
  36. Munkres, J.: 1955, 'Algorithms for the Assignment and Transportation Problems'. Journal of the Society of Industrial and Applied Mathematics 5(1), 32-38.
  37. Och, F. J. and H. Ney: 2002, 'Discriminative Training and Maximum Entropy Models for Statistical Machine Translation'. In: Proceedings of the 40th annual ACL Conference. Philadelphia, PA, pp. 295-302.
  38. Papineni, K., S. Roukos, T. Ward, and W. Zhu: 2002, 'BLEU: a method for auto- matic evaluation of machine translation'. In: Proceedings of the 40th ACL. pp. 311-318.
  39. Pinkham, J. and M. Smets: 2002, 'Modular MT with a learned bilingual dictionary: rapid deployment of a new language pair'. In: Coling. Taipei, Taiwan, pp. 800- 806.
  40. Pytlik, B. and D. Yarowsky: 2006, 'Machine translation for languages lacking bitext via multilingual gloss transduction'. In: Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, "Visions for the Future of Machine Translation". Cambridge, Massachusetts, USA, pp. 156-165.
  41. METIS-II.tex; 10/03/2010; 16:08; p.38
  42. Snover, M., B. Dorr, R. Schwartz, L. Micciulla, and J. Makhoul: 2006, 'A Study of Translation Edit Rate with Targeted Human Annotation'. In: Proceedings of Association for Machine Translation in the Americas (AMTA 2006). pp. 223- 231.
  43. Szopa, R.: 2007, 'LRBL. A Rule-Based Lemmatizer (with rules for Dutch)'. Technical report, Centre for Computational Linguistics, Leuven, Belgium.
  44. Tambouratzis, G., S. Sofianopoulos, V. Spilioti, M. Vassiliou, O. Yannoutsou, and M. S.: 2006, 'Pattern matching-based system for Machine Translation (MT)'. In: Proceedings of Advances in Artificial Intelligence: 4th Hellenic Conference on AI, SETN 2006. Heraklion, Crete, pp. 345-355.
  45. Van Eynde, F. .: 2004, 'Part of Speech Tagging en Lemmatisering van het Corpus Gesproken Nederlands'. Annotation protocol, Centrum voor Computer- linguïstiek, Leuven, Belgium.
  46. Vandeghinste, V.: 2005, 'Manual for ShaRPa 2.1'. User manual, Centre for Computational Linguistics, Leuven, Belgium.
  47. Vandeghinste, V.: 2008, 'A Hybrid Modular Machine Translation System'. Phd thesis, Netherlands Graduate School of Linguistics, Leuven, Belgium.
  48. Vandeghinste, V., P. Dirix, I. Schuurman, S. Markantonatou, S. Sofianopoulos, M. Vassiliou, O. Yannoutsou, T. Badia, M. Melero, G. Boleda, M. Carl, and P. Schmidt: 2008, 'Evaluation of a Machine Translation System for Low Resource Languages: METIS-II'. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC). Marrakech, Morocco, p. 96.
  49. Vossen, P., L. Bloksma, and B. P.: 1999, 'The Dutch Wordnet'. Technical report, University of Amsterdam, Amsterdam, NL.
  50. Whitelock, P.: 1991, 'Shake-and-Bake Translation'. Unpublished Draft.
  51. Whitelock, P.: 1992, 'Shake-and-Bake Translation'. In: Proceedings of the COL- ING92. Nantes, France, pp. 784-791.
  52. Zwarts, S. and M. Dras: 2007, 'Syntax-based Word Reordering in Phrase-Based Statistical Machine Translation; Why Does it Work?'. In: Proceedings of MT Summit XI. Copenhagen. Denmark, pp. 559-566.

Related papers

METIS-II: Low Resources Machine Translation: Background, Implementation, Results and Potentials
Marina Vassiliou

METIS, 2008

METIS-II was a EU-FET MT project running from October 2004 to September 2007, which aimed at translating free text input without resorting to parallel corpora, but relying only on monoligual target language corpora and employing a palette of statistical, pattern-matching and rule-based methods. The METIS-II project has four partners, translating from their 'home' languages Greek, Dutch, German, and Spanish into English. The idea was to use 'basic' linguistic tools and representations and to link them with patterns and statistics from the monolingual target-language corpus. The paper reports on the background of the ideas, their implementation, the resources used, and the results obtained. It also gives a few examples of how METIS-II has continued beyond its lifetime and the original scope of the project. On the basis of the results and experiences obtained, we conclude that the approach is promising and offers the potential for development in various directions.

View PDFchevron_right
Evaluation of a Machine Translation System for Low Resource Languages: METIS-II
Marina Vassiliou, Olga Yannoutsou

2008

In this paper we describe the METIS-II system and its evaluation on each of the language pairs: Dutch, German, Greek, and Spanish to English. The METIS-II system envisaged developing a data-driven approach in which no parallel corpus is required and in which no full parser or extensive rule sets are needed. We describe the evaluation on a development test set and on a test set taken from Europarl, and compare our results with SYSTRAN. We also provide some further analysis, namely researching the impact of the number and source of the reference translations and analysing the results according to test text type. The results are expectably lower for the METIS system, but not at an unattainable distance from a mature system like SYSTRAN.

View PDFchevron_right
METIS-II: Low-Resource MT for German to English
Michael Carl

Journal for Language Technology and Computational Linguistics

METIS-II was a EU-FET MT project running from October 2004 to September 2007, which aimed at translating free text input without resorting to parallel corpora. The idea was to use 'basic' linguistic tools and representations and to link them with patterns and statistics from the monolingual target-language corpus. The METIS-II project has four partners, translating from their 'home' languages Greek, Dutch, German, and Spanish into English. The paper outlines the basic ideas of the project, their implementation, the resources used, and the results obtained. It emphazises on the German implementation. 2 Introduction Starting in October 2004, METIS-II was the continuation of METIS-I (IST-2001-32775) Dologlou et al. (2003). Like METIS-I, METIS-II aims at translating free text input by taking advantage of a combination of statistical, pattern-matching and rule-based methods. The METIS-II project has four partners, each translating from their 'home' languages Greek, Dutch, German, and Spanish into English. The following goals and premises were defined for the project: 1. use 'basic' NLP tools and resources, 2. use bilingual handmade dictionaries, 3. use a monolingual target-language corpus, 4. use translation units within the sentence boundary, 5. allow different tag sets for SL and TL possible, Crucially, parallel corpora are not required, and their usage was excluded within METIS-II. The rationale behind this was to develop prototypes of MT systems which would be suitable to translate 'small languages', i.e. language pairs for which parallel texts are difficult to come by. A basic set of NLP tools is nonetheless required for these languages, albeit very basic. The availability of the monolingual target language corpus,

View PDFchevron_right
METIS-II: Machine Translation for Low Resource Languages
Ineke Schuurman, Stella Markantonatou

2006

In this paper we describe a machine translation prototype in which we use only minimal resources for both the source and the target language. A shallow source language analysis, combined with a translation dictionary and a mapping system of source language phenomena into the target language and a target language corpus for generation are all the resources needed in the described system. Several approaches are presented.

View PDFchevron_right
Using Monolingual Corpora for Statistical Machine Translation: The METIS System
Stella Markantonatou

In this article the principles of the METIS Machine Translation system are presented. METIS employs an extensive tagged and lemmatised corpus of texts in the target language, coupled with bilingual lexica covering the desired pairs of source-target languages. To generate a high-quality translation, the METIS system is provided with statistical tools enabling it to extract linguistic knowledge from the annotated corpus of the target language. The advantage of this approach is that, although no grammars need to be provided explicitly, grammatical translations are retrieved from the corpus by using pattern matching techniques.

View PDFchevron_right

Related topics

  • Cognitive Science
  • Computer Science
  • Artificial Intelligence
  • Computational Linguistics
  • Machine Translation
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved