Academia.eduAcademia.edu

Outline

Title
Abstract
Experimental Design
Future Work
Conclusion and Outlook
Experimental Data Used
Similarity Measures in Previous Works
Method
Discussion and Future Work
Universal Data Format
SL Analysis 4.1.1 Tokeniser
Making Use of Statistical Units (N-Grams)
Availability of Our Data
Introduction: Why a Definition is Needed
The Database
Acknowledgements
Coverage Analysis
Experimental Set-Up
Results and Discussion
Results with the Resource Only
Experimental Results
Limitations of String-Based Phrasal SMT
Data
Related Work
Experiments and Results
Conclusions and Future Work
Statistical Machine Translation
Machine Learning Approach for Hypotheses Selection
Experimental Setting
Hypotheses Selection Method
Discussion
Introduction
Related Works
Dictionary Design
Conclusion
MT System Development Methodology
Introduction: Background of Metis-II
Source Language Analysis
Other Cases
Results
Methodology
Conclusions
The Near and Not Too Distant Future
References
All Topics
Computer Science
Natural Language Processing

Monolingual Corpus-based MT using chunks

Profile image of Marina VassiliouMarina VassiliouProfile image of Olga YannoutsouOlga Yannoutsou

2005, MT Summit X

Abstract
sparkles

AI

The paper presents advancements in Example-based Machine Translation (EBMT) showcased at the MT Summit X workshop. Highlighting a variety of innovative approaches and techniques, it discusses semantic and type-driven methods, the integration of multiple techniques, and the evolution of EBMT since its inception. The introduction of monolingual target language corpora and fragment retrieval methods exemplifies the workshop's focus on improving translation performance, reflecting the dynamic and collaborative nature of EBMT research.

Related papers

Hybrid data-driven models of machine translation
Declan Groves

Machine Translation, 2005

This paper presents an extended, harmonised account of our previous work on combining subsentential alignments from phrase-based statistical machine translation (SMT) and example-based MT (EBMT) systems to create novel hybrid data-driven systems capable of outperforming the baseline SMT and EBMT systems from which they were derived. In previous work, we demonstrated that while an EBMT system is capable of outperforming a phrase-based SMT (PBSMT) system constructed from freely available resources, a hybrid ‘example-based’ SMT system incorporating marker chunks and SMT subsentential 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. Unlike the previous research, here we use the Europarl training and test sets, which are fast becoming the standard data in the field. On these data sets, while all hybrid ‘statistical’ EBMT variants still fall short of the quality achieved by the baseline PBSMT system, we show that adding the marker chunks to create a hybrid ‘example-based’ SMT system outperforms the two baseline systems from which it is derived. Furthermore, we provide further evidence in favour of hybrid systems by adding an SMT target-language model to the EBMT system, and demonstrate that this too has a positive effect on translation quality. We also show that many of the subsentential alignments derived from the Europarl corpus are created by either the PBSMT or the EBMT system, but not by both. In sum, therefore, despite the obvious convergence of the two paradigms, the crucial differences between SMT and EBMT contribute positively to the overall translation quality. The central thesis of this paper is that any researcher who continues to develop an MT system using either of these approaches will benefit further from integrating the advantages of the other model; dogged adherence to one approach will lead to inferior systems being developed.

View PDFchevron_right
Corpora in machine translation
Hanne Moa

2005

View PDFchevron_right
D 6 . 3 : Improved Corpus-based Approaches
Lianet Sepúlveda Torres

2016

View PDFchevron_right
A new hybrid approach enabling MT for languages with little resources
Peter Dirix, Ineke Schuurman

In this paper, we combine techniques from rule-based and corpus-based MT in a hybrid approach. We only use a dictionary, basic analytical resources and a monolingual targetlanguage corpus in order to enable the construction of an MT system for lesser-resourced languages. Statistical and example-based systems usually do not involve a lot of linguistic notions. Cutting up sentences in linguistically sound subunits improves the quality of the translation. Demarcating clauses, verb groups, noun phrases, and prepositional phrases restricts the number of possible translations and hence also the search space. The sentence chunks are translated using a dictionary and a limited set of mapping rules. By bottom-up matching the different translated items and higher-level structure with the database information, one or more plausible translated sentences are constructed. A search engine ranks them using the frequencies of occurence and the matching accuracy in the target-language corpus.

View PDFchevron_right
MT model space: statistical versus compositional versus example-based machine translation
Dekai Wu

Machine Translation, 2007

We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.

View PDFchevron_right
Contextual Constraints for MT
Kurt Eberle

IEEE Transactions on Medical Imaging, 2000

We outline an experimental machine translation system currently under development at the Institute for Computational Linguistics which aims at flexibility with respect to the level of transfer. The core of the system is a bidirectional transfer system using LFG-grammars for source and target languages. If translation is not possible on the basis of the linguistic informa- tion provided by the

View PDFchevron_right
Gaijin: A Bootstrapping, Template Driven Approach to Example-Based MT
Tony Veale

Example-based Machine Translation (EBMT) is a recent approach to MT that offers robustness, scalability and graceful degradation, deriving as it does its competence not from explicit linguistic models of source and target languages, but from the wealth of bilingual corpora that are now available. Gaijin is such a system, employing statistical methods, string-matching, case-based reasoning and template-matching to provide a linguistics-lite EBMT solution. The only linguistics employed by Gaijin is a psycholinguistic constraint-the marker hypothesis-that is minimal, simple to apply, and arguably universal. The scope and current state of Gaijin is described, and some initial evaluation results are reported.

View PDFchevron_right
Scaling the ISLE framework: Use of existing corpus resources for validation of MT evaluation metrics across languages
Michelle Vanni

Proceedings of LREC, 2002

This paper describes a machine translation (MT) evaluation (MTE) research program which has benefited from the availability of two collections of source language texts and the results of processing these texts with several commercial MT engines (DARPA 1994. The methodology entails the systematic development of a predic tive relationship between discrete, well-defined MTE metrics and specific information processing tasks that can be reliably performed with output of a given MT system. Unlike tests used in initial experiments on automated scoring (Jones and Rusk 2000), we employ traditional measures of MT output quality, selected from the International Standards for Language Engineering (ISLE) framework: Coherence, Clarity, Syntax, Morphology, General and Domain-specific Lexical robustness, to include Named-entity translation. Each test was originally validated on MT output produced by three Spanish-to-English systems (1994 DARPA MTE). We validate tests in the present work, however, with material taken from the MT Scale Evaluation research program produced by Japanese-to-English MT systems. Since Spanish and Japanese differ structurally on the morphological, syntactic, and discourse levels, a comparison of scores on tests measuring these output qualities should reveal how structural similarity, such as that enjoyed by Spanish and English, and structural contrast, such as that found between Japanese and English, affect the linguistic distinctions which must be accommodated by MT systems. Moreover, we show that metrics developed using Spanish-English MT output are equally effective when applied to Japanese-English MT output.

View PDFchevron_right
Proceedings of the Second Joint EM+/CNGL Workshop “Bringing MT to the User: Research on Integrating MT in the Translation Industry” (JEC ’10)
Ventsislav Zhechev

For a long time, machine translation and professional translation vendors have had a contentious relation. However, new tools, computing platforms, and business models are changing the fundamentals of this relationship. I will review the main trends in the area while emphasising both past causes of failure and main drivers of success. Invited Speaker As SDL Language Weaver's CTO, Daniel leads the R&D efforts focused on automated translation technology. Prior to cofounding Language Weaver, Daniel was a Research Associate Professor in Computer Science at the University of Southern California, a position he still holds. He is recognised as a leading authority in natural language processing, machine translation, discourse parsing and text summarisation. Daniel has more than 20 patents awarded or pending and has published an MIT press book and more than 100 peer reviewed articles. Daniel received his Ph.D. in Computer Science from the University of Toronto.

View PDFchevron_right
Corpus encoding and integration for English-Spanish MT
Alejandro Curado Fuentes

Explorations across Languages and Corpora, 2011

Machine Translation applications have achieved significant results for specialised discourse (cf. Wilks, 2009). The conjunction of web-based resources and hybrid systems seems to render some note-worthy advances. In addition, a novel technique outlines a context approach MT that may be coming into its own (cf. Carbonell et al., 2006). This context-based method focuses on the management of a massive target corpus alone (i.e., processes the translated data from a bilingual dictionary in context). Our own project applies these techniques to the translation of English to Spanish, and attempts to manage and decode n-grams from the source text to the Spanish corpus, via their integration in databases. The process requires as much context (text) as possible and may be partially tested by working with a small specific corpus. The n-gram classification should enable the step called 'flooding' for the scoring of the best translation options.

View PDFchevron_right

References (184)

  1. Ralf D. Brown. 1996. Example-Based Machine Translation in the PANGLOSS System. In Pro- ceedings of the Sixteenth International Con- ference on Computational Linguistics, pages 169-174, Copenhagen, Denmark. http://- www.cs.cmu.edu/˜ralf/papers.html.
  2. Ralf D. Brown. 2001. Transfer-Rule Induction for Example-Based Translation. In Proceedings of the Workshop on Example-Based Machine Translation, September. http://www.cs.- cmu.edu/˜ralf/papers.html.
  3. Ralf D. Brown. 2004. A Modified Burrows- Wheeler Transform for Highly-Scalable Example-Based Translation. In Machine Translation: From Real Users to Research, Pro- ceedings of the 6th Conference of the Association for Machine Translation in the Americas (AMTA- 2004), volume 3265 of Lecture Notes in Artificial Intelligence, pages 27-36. Springer Verlag, September-October. http://www.cs.- cmu.edu/˜ralf/papers.html.
  4. William A. Gale, Kenneth W. Church, and David Yarowsky. 1992. One Sense Per Discourse. In Speech and Natural Language: Proceed- ings of a Workshop Held at Harriman, New York, pages 233-237, February. http://- www.ldc.upenn.edu/H/H92/.
  5. Nano Gough and Andy Way. 2003. Controlled Generation in Example-Based Machine Transla- tion. In Proceedings of the Ninth Machine Trans- lation Summit (MT Summit IX), pages 133-140.
  6. Linguistic Data Consortium. 1997. Hansard Cor- pus of Parallel English and French. Linguis- References Toni Badia. 2005. An n-gram approach to exploiting monolingual corpus for MT. In Second EBMT Work- shop.
  7. Thorsten Brants. 2000. A Statistical Part-of-Speech Tagger? In Proceedings of TUANLP, pages 224-231.
  8. Chris Brew. 1992. Letting the Cat out of the Bag: Gen- eration for Shake & Bake MT. In Proceedings of COL- ING92.
  9. Yunbo Cao and Hang Li. 2000. Base Noun Phrase Translation: Using Web Data and the EM Algorithm. In COLING.
  10. Michael Carl, Ecaterina Rascu, and Paul Schmidt. 2005. Using template grammars for shake & bake paraphras- ing. In EAMT.
  11. Michael Carl. 2003. Inducing Translation Grammars from Bracket Alignments. In Recent Advances in Example-Based Machine Translation.
  12. Michael Carl. 2005. KURD. IAI, electronic working pa- per 38. forthcoming.
  13. Ilyas Cicekli and H. A Guvenir. 2003. Learning Transla- tion Templates from Bilingual Translation Examples. In Recent Advances in Example-Based Machine Trans- lation.
  14. Ilyas Cicekli. 2005. Learning Translation Templates with Type Constraints. In Workshop on EBMT.
  15. Joshua Goodman. 2002. The State of the Art in Lan- guage Modeling. In Tutorial Presented at AMTA. Nano Gough and Andy Way. 2004. Example-Based Con- trolled Translation. In EAMT.
  16. Nizar Habash and Bonnie Dorr. 2002. Handling Trans- lation Divergences: Combining Statistical and Sym- bolic Techniques in Generation-Heavy Machine Trans- lation. In AMTA.
  17. Christos Malavazos and Stelios Piperidis. 2000. Appli- cation of Analogical Modelling to Example Based Ma- chine Translation. In COLING.
  18. A. Stolcke. 2002. SRILM -An Extensible Language Modeling Toolkit. In ICSLP.
  19. P. Whitelock, 1991. Shake-and-Bake Translation. Un- published Draft.
  20. P. Whitelock. 1992. Shake-and-Bake Translation. In Proceedings of the COLING92.
  21. References T. Badia, G. Boleda, M. Melero, and A. Oliver. 2005. An n-gram approach to exploiting a monolingual corpus for Machine Translation. In Proceedings of the EBMT Workshop 2005, Phuket (this volume).
  22. T. Brants. 2001. TnT -A Statistical Part- of-Speech Tagger. Published online at http://www.coli.uni-sb.de/thorsten/tnt.
  23. M. Carl, P. Schmidt, and J. Schütz. 2005. Re- versible Template-based Shake & Bake Gener- ation. In Proceedings of the EMBT Workshop 2005, this volume.
  24. P. Dirix. 2002a. The METIS Project: Lexical Re- sources. Internship Report, KULeuven.
  25. P. Dirix. 2002b. The METIS Project: Tag-mapping rules. Paper, KULeuven.
  26. Y. Dologlou, S. Markantonatou, G. Tambouratzis, O. Yannoutsou, A. Fourla, and N. Ioannou, 2003. Using Monolingual Corpora for Statis- tical Machine Translation: The METIS Sys- tem. In Proceedings of EAMT -CLAW 2003, Dublin, pp. 61-68.
  27. G. Grefenstette. 1999. The World Wide Web as a Resource for Example-Based Machine Trans- lation Tasks. ASLIB, Translating and the Com- puter 21. London.
  28. S. Markantonatou, S. Sofianopoulos, V. Spilioti, Y. Tambouratzis, M. Vassiliou, O. Yannoutsou, and N. Ioannou, 2005. Monolingual Corpus- based MT using Chunks. In Proceedings of the EBMT Workshop 2005, Phuket (this volume).
  29. H. Somers. 2003. An overview of EBMT. In M. Carl and A. Way (ed.), Recent advances in example-based machine translation, Kluwer Academic Publishers, Dordrecht.
  30. V. Vandeghinste. 2005. Manual for ShaRPa 2.0. Internal Document. Centre for Computational Linguistics, Leuven.
  31. V. Vandeghinste, P. Dirix, and I. Schuurman. 2005. Example-based Translation without Par- allel Corpora: First experiments on a proto- type. In Proceedings of the EBMT Workshop 2005, Phuket (this volume).
  32. V. Vandeghinste and E. Tjong Kim Sang. 2004. Using a Parallel Transcript/Subtitle Corpus for Sentence Compression. In Proceedings of LREC2004. ELRA. Paris.
  33. F. Van Eynde. 2004. Tagging and Lemmatisation for the Spoken Dutch Corpus. Internal report.
  34. P. Vossen, L. Bloksma, and P. Boersma. 1999. The Dutch WordNet. University of Amsterdam. References Jiang Chen and Jian-Yun Nie. 2000. Automatic construction of parallel English-Chinese cor- pus for cross-language information retrieval. In Proceedings of the Sixth Conference on Ap- plied Natural Language Processing, pages 21- 28, Seattle.
  35. Xiaoyi Ma and Mark Liberman. 1999. BITS: a method for bilingual text search over the web. In Proceedings of MT Summit VII, Septem- ber. Philip Resnik and Noah A. Smith. 2003. The web as a parallel corpus. Computational Lin- guistics, 29(3):349-380.
  36. Masao Utiyama and Hitoshi Isahara. 1993. Re- liable measures for aligning Japanese-English news articles and sentences. In Proceedings of ACL-93, pages 72-79, Columbus, Ohio.
  37. References P. Brown, J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, R. M. Mercer and P. Roossin. 1988: A statistical approach to French/English translation. Second International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages. Pittsburgh, Pennsylvania: Carnegie-Mellon University.
  38. J. Carbonell, K. Probst, E. Peterson, C. Monson, A. Lavie, R. Brown, and L. Levin. 2002. Automatic rule learning for resource-limited MT. In: S. D. Richardson (ed.) Machine translation: from research to real users, 5th Conference of the Association for Machine Translation in the Americas, AMTA 2002, Tiburon, CA, USA, October 2002 (Berlin: Springer), 1-10.
  39. M. Carl, and A. Way, eds. 2003. Recent advances in example-based machine translation. Dordrecht: Kluwer Academic Publishers.
  40. E. Charniak, K. Knight, and K. Yamada. 2003. Syntax-based language models for statistical machine translation. MT Summit IX: proceedings of the Ninth Machine Translation Summit, New Orleans, USA, September 23-27, 2003; 40-46.
  41. N. Gough and A. Way. 2004. Robust large-scale EBMT with marker-based segmentation. TMI- 2004: proceedings of the Tenth International Conference on Theoretical and Methodological Issues in Machine Translation, October 4-6, 2004, Baltimore, Maryland, USA, 95-104.
  42. P. Koen, and K. Knight. 2003. Feature-rich statistical translation of noun phrases. ACL-2003: 41st Annual Meeting of the Association for Computational Linguistics, July 7-12, 2003, Sapporo, Japan T. S. Kuhn. 1962. The structure of scientific revolutions. Chicago: University of Chicago. (International Encyclopedia of Unified Science, vol.2, no.
  43. B. Lavoie, M. White, and T. Korelsky. 2001. Inducing lexico-structural transfer rules from parsed bi-texts. ACL-EACL 2001 workshop "Data-driven Machine Translation", July 7, 2001, Toulouse, France, 17-24.
  44. K. McTait. 2003. Translation patterns, linguistic knowledge and complexity in an approach to EBMT. In: Carl and Way (2003), 307-338.
  45. H. Maruyama and H. Watanabe. 1992. Tree cover search algorithm for example-based translation. Third International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages (TMI-90). Proceedings, 11-13 June 1990, Austin, Texas, 173-184.
  46. A. Menezes and S. D. Richardson. 2001. A best- first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora. ACL-EACL 2001 workshop "Data- driven Machine Translation", July 7, 2001, Toulouse, France, 39-46. Repr. in: Carl and Way (2003), 421-442.
  47. M. Nagao. 1984. A framework of a mechanical translation between Japanese and English by analogy principle. In: A.Elithorn and R.Banerji (eds.) Artificial and human intelligence (Amsterdam: North-Holland), 173-180.
  48. S. Sato and M. Nagao. 1990. Towards memory- based translation. In: H. Karlgren (ed.) Coling- 90: papers presented to the 13th International Conference on Computational Linguistics, Helsinki, August 1990; vol.3, 247-252.
  49. H. Somers. 1999. Review article: example-based machine translation. Machine Translation 14(2), 113-157. Revised as: An overview of EBMT. In Carl and Way (2003), 3-57.
  50. H. Somers, I. McLean and D. Jones. 1994. Experiments in multilingual example-based generation. CSNLP 1994: 3rd Conference on the Cognitive Science of Natural Language Processing, Dublin City University, 6-8 July 1994.
  51. E. Sumita, H. Iida, and H. Kohyama. 1990. Translating with examples: a new approach to machine translation. Third International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages (TMI-90). Proceedings, 11-13 June 1990, Austin, Texas, 203-212.
  52. E. Sumita. 2003. An example-based machine translation system using DP-matching between word sequences. In Carl and Way (2003), 189- 209. D. Turcato and F. Popowich. 2003. What is example-based machine translation? In: Carl and Way (2003), 59-81.
  53. H. Watanabe, S. Kurohashi, and E. Aramaki. 2003. Finding translation patterns from paired source and target dependency structures. In Carl and Way (2003), 397-420.
  54. T. Watanabe and E. Sumita. 2002. Statistical machine translation based on hierarchical phrase alignment. Ninth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-2002), March 13-17, 2002, Keihanna, Japan; 188-198.
  55. D. Wu. 2000. Bracketing and aligning words and constituents in parallel text using stochastic inversion transduction grammars. In: J. Véronis (ed.) Parallel text processing: alignment and use of translation corpora (Dordrecht: Kluwer Academic Publishers), 139-167.
  56. References Didier Bourigault and Cécile Fabre. 2000. Ap- proche linguistique pour l'analyse syntaxique de corpus. Cahiers de Grammaire, (25):131- 151. Toulouse le Mirail.
  57. P. F. Brown, S. A. Della Pietra, V. J. Della Pietra, and R. L. Mercer. 1993. The Math- ematics of Statistical Machine Translation: Parameter Estimation. Computational Lin- guistics, 19(2):263-311.
  58. Yuang Ding and Martha Palmer. 2004. Auto- matic learning of parallel dependency treelet pairs. In First International Joint Conference on Natural Language Processing.
  59. Daniel Gildea. 2003. Loosely tree-based align- ment for machine translation. In ACL.
  60. Almut Silja Hildebrand, Matthias Eck, Stephan Vogel, and Alex Waibel. 2005. Adaptation of the translation model for statistical machine translation based on information retrieval. In 10th EAMT, pages 133-142, Budapest, Hon- gary, May 30-31.
  61. P. Koehn, F.J. Och, and D. Marcu. 2003. Sta- tistical Phrase-Based Translation. In Pro- ceedings of HLT, pages 127-133.
  62. Philipp Koehn. 2004. Pharaoh: a Beam Search Decoder for Phrase-Based SMT. In Proceed- ings of AMTA, pages 115-124.
  63. Evgeny Matusov, Stephan Kanthak, and Her- mann Ney. 2005. Efficient statistical ma- chine translation with constraint reordering. In 10th EAMT, pages 181-188, Budapest, Hongary, May 30-31.
  64. £ ¦¥ ¤ § ¨¥ 9 @ 7A B DC ! ¡ % E 8F HG A 2318 I'd like another cup of coffee. 2296 May I have another cup of coffee? 1993 Another coffee, please. 1982 May I trouble you for another cup of coffee? 1982 Can I get some more coffee? 530 Another cup of coffee, please. 516 Another cup of coffee.
  65. Can I have another cup of coffee? 337 May I get some more coffee? 205 May I trouble you for another cup of coffee, please? I P ! F HQ 5R S# 0% (' ¡ 924 Can you include some small change? 922 Can you include some small change, please? 899 Would you include some small change? 896 Include some small change, please.
  66. I'd like to have smaller bills mixed in. 895 Please change this into small money. 895 Will you include some small change? 885 Could you include some small change, please?
  67. May I have some small change, too? References
  68. Peter E. Brown, Vincent J. Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statis- tical machine translation: Parameter estima- tion. Computational Linguistics, Special Is- sue on Using Large Corpora: II, 19(2):263- 311, March.
  69. Michael Carl. 1998. A constructivist approach to machine translation. In Proceedings of NeMLaP'98, Sydney.
  70. Nizar Habash. 2002. Generation-heavy hybrid machine translation. In Proceedings of the International Natural Language Generation Conference (INLG'02), New York.
  71. Zellig Harris. 1954. Distributional structure. Word, 10:146-162.
  72. Zellig Harris. 1982. A grammar of English on mathematical principles. John Wiley & Sons, New York.
  73. Yves Lepage and Guilhem Peralta. 2004. Using paradigm tables to generate new ut- terances similar to those existing in linguistic resources. In Proceedings of LREC-2004, vol- ume 1, pages 243-246, Lisbonne, May.
  74. Yves Lepage. 1998. Solving analogies on words: an algorithm. In Proceedings of COLING-ACL'98, volume I, pages 728-735, Montréal, August.
  75. Yves Lepage. 2004. Lower and higher esti- mates of the number of "true analogies" be- tween sentences contained in a large multi- lingual corpus. In Proceedings of COLING- 2004, volume 1, pages 736-742, Genève, Au- gust.
  76. Naomi Sager. 1981. Natural language infor- mation processing: a computer grammar of English and its applications. Adelson-Wesley, Reading, Massachusetts.
  77. Morris Salkoff. 1973. Une grammaire en chaîne du français. Dunod, Paris.
  78. Manabu Sasayama, Fuji Ren, and Shigo Kuroiwa. 2003. Super-function based Japanese-English machine translation sys- tem. In Proceedings of Natural Language Processing and Knowledge Engineering, vol- ume 1, pages 555-560, Beijing, October.
  79. Satoshi Sato. 1991. Example-based Machine Translation. Ph.d. thesis, Kyoto University, September.
  80. Eiichiro Sumita and Hitoshi Iida. 1991. Ex- periments and prospects of example-based machine translation. In Proceedings of the 29th Conference on Association for Compu- tational Linguistics, pages 185-192, Morris- town, NJ, USA. Association for Computa- tional Linguistics.
  81. Kazuhide Yamamoto. 2004. Interaction be- tween paraphraser and transfer for spoken language translation. Journal of Natural Language Processing, 11(5):63-86, October.
  82. References Y. Al-Onaizan, U. Germann, U. Hermjakob, K. Knight, P. Koehn, D. Marcu, & K. Yamada. 2000. Translating with Scarce Resources. American As- sociation for Artificial Intelligence Conference (AAAI'00), 30 July -3 August, Austin, Texas, pages 672-678 (T Uhttp://www.isi.edu/natural- language/projects/rewriteU T).
  83. S. Boutsis, P. Prokopidis, V. Giouli & S. Piperidis. 2000. A Robust Parser for Unrestricted Greek Text. In "Proceedings of the Second International Conference on Language Resources and Evalua- tion", 31 May-2 June, Athens, Greece, Vol. 1, pp. 467-482.
  84. P. Brown, J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, J. Lafferty, R. Mercer & P. S. Roosin. 1990. A Statistical Approach to Machine Transla- tion. Computational Linguistics, 16(2):79-85.
  85. L. Cranias, H. Papageorgiou & S. Piperidis. 1997. Example Retrieval from a Translation Memory. Natural Language Engineering, 3:255-277.
  86. I. Dologlou, S. Markantonatou, G. Tambouratzis, O. Yannoutsou, A. Fourla & N. Ioannou. 2003. Us- ing Monolingual Corpora for Statistical Machine Translation. In "Proceedings of EAMT/CLAW 2003", Dublin, Ireland, 15-17 May.
  87. H. Dyvik. 1995. Exploiting Structural Similarities in Machine Translation. Computers and the Hu- manities, 28:225-234.
  88. ILSP Internal Document 2004. Specifications for METIS lexicon.
  89. N. Ioannou. 2003. METIS: Statistical Machine Translation Using Monolingual Corpora. In "Proceedings of the Workshop on Text Process- ing for Modern Greek: From Symbolic to Statisti- cal Approaches" (held in conjunction with the 6 th International Conference of Greek Linguistics), Rethymno, Greece, 20 September. ISBN:960- 88268-0-2.
  90. P. Labropoulou, E. Mantzari & M. Gavrilidou. 1996. Lexicon-Morphosyntactic Specifications: Language Specific Instantiation (Greek), PP- PAROLE, MLAP 63-386 report. METEOR: TUhttp://www-2.cs.cmu.edu/~banerjee/
  91. K. McTait. 2003. Translation Patterns, Linguistic Knowledge and Complexity in EBMT. In "Recent Advances in Example-Based Machine Transla- tion", M. Carl and A. Way (eds.) Kluwer Aca- demic Publishers, pp. 307-338.
  92. M. Nagao. 1984. A Framework of a Mechanical Translation between Japanese and English by Analogy Principle. In "Artificial and Human In- telligence", A. Elithorn and R. Banerji (eds). North-Holland.
  93. NIST: TUhttp://www.nist.gov/speech/tests/mt/UT
  94. A. Papineni, S. Roukos, T. Ward & W. J. Zhu. 2002. Bleu, a method for automatic evaluation of Machine Translation. In "Proceedings of the 40P th P Annual Meeting of the Association for Computa- tional Linguistics", Philadelphia (USA), pages 311-318.
  95. M. Popovic and H. Ney. 2005. Exploiting Phrasal Lexica and Additional Morpho-syntactic Lan- guage Resources for Statistical Machine Transla- tion with Scarce Training Data. EAMT 10 th An- nual Conference, 30-31 May, Budapest, Hungary.
  96. V. Vandeghinste 2005. Manual for ShaRPa 2.0. Internal Report, Centre for Computational Lin- guistics, K.U.Leuven.
  97. A. Way 2003. Translating with Examples: The LFG-DOT Models of Translation, In "Recent Ad- vances in Example-Based Machine Translation", M. Carl and A. Way (eds.). Kluwer Academic Publishers, pages 443-472.
  98. Alshawi, Hiyan, Srinivas Bangalore, and Shona Douglas. Learning dependency translation models as collections of finite-state head transducers. Computational Linguistics, 26(1):45-60, 2000.
  99. Aue, Anthony, Arul Menezes, Robert C. Moore, Chris Quirk, and Eric Ringger. Statistical machine translation using labeled semantic dependency graphs. TMI 2004.
  100. Charniak, Eugene, Kevin Knight, and Kenji Yamada. Syntax-based language models for statistical machine translation. MT Summit 2003.
  101. Cherry, Colin and Dekang Lin. A probability model to improve word alignment. ACL 2003.
  102. Chickering, David Maxwell. The WinMine Toolkit. Microsoft Research Technical Report: MSR-TR-2002- 103. Ding, Yuan and Martha Palmer. Automatic learning of parallel dependency treelet pairs. IJCNLP 2004.
  103. Heidorn, George. (2000). "Intelligent writing assistance". In Dale et al. Handbook of Natural Language Processing, Marcel Dekker.
  104. Koehn, Philipp, Franz Josef Och, and Daniel Marcu. Statistical phrase based translation. NAACL 2003.
  105. Lin, Dekang. A path-based transfer model for machine translation. COLING 2004.
  106. Menezes, Arul and Stephen D. Richardson. A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora. In Recent Advances in Example-Based Machine Translation, M. Carl & A. Way, Eds, Kluwer Academic Publishers, 2003.
  107. Och, Franz Josef and Hermann Ney. A systematic comparison of various statistical alignment models, Computational Linguistics, 29(1):19-51, 2003.
  108. Och, Franz Josef. Minimum error rate training in statistical machine translation. ACL 2003.
  109. Och, Franz Josef, et al. A smorgasbord of features for statistical machine translation. HLT/NAACL 2004.
  110. Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. BLEU: a method for automatic evaluation of machine translation. ACL 2002.
  111. Quirk, Chris, Arul Menezes, and Colin Cherry. Dependency Tree Translation. Microsoft Research Technical Report: MSR-TR-2004-113.
  112. Ringger, Eric, et al. Linguistically informed statistical models of constituent structure for ordering in sentence realization. COLING 2004.
  113. Thurmair, Gregor. Comparing rule-based and statistical MT output. Workshop on the amazing utility of parallel and comparable corpora, LREC, 2004.
  114. Vogel, Stephan, Ying Zhang, Fei Huang, Alicia Tribble, Ashish Venugopal, Bing Zhao, and Alex Waibel. The CMU statistical machine translation system. MT Summit 2003.
  115. Way, A. and N. Gough. Comparing Example-Based and Statistical Machine Translation. Journal of Natural Language Engineering, June 2005
  116. Wu, Dekai. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational Linguistics, 23(3):377-403, 1997.
  117. Yamada, Kenji and Kevin Knight. A syntax-based statistical translation model. ACL, 2001.
  118. Britta Bauer, Sonja Nießen and Hermann Heinz. 1999. Towards an Automatic Sign Language Translation System. In Proceedings of the Inter- national Workshop on Physicality and Tangibility in Interaction: Towards New Paradigms for In- teraction Beyond the Desktop, Siena, Italy.
  119. Ralf Brown. 1999. Adding Linguistic Knowledge to a Lexical Example-based Translation System. In Proceedings of the 8th International Conference on Theoretical and Methodological Issues in Ma- 5 http://www.ircset.ie chine Translation (TMI-99), Chester, England, pp.22-32.
  120. Michael Carl and Andy Way (eds). 2003. Recent Advances in Example-Based Machine Translation. Kluwer, Dordrecht, The Netherlands.
  121. Nano Gough and Andy Way. 2004a. Example-Based Controlled Translation. In Proceedings of the Ninth EAMT Workshop, Valetta, Malta, pp.73- 81. Nano Gough and Andy Way. 2004b. Robust Large- Scale EBMT with Marker-Based Segmentation. In Proceedings of the Tenth Conference on The- oretical and Methodological Issues in Machine Translation (TMI-04), Baltimore, MD., pp.95- 104. Thomas Green. 1979. The Necessity of Syntax Markers. Two experiments with artificial lan- guages. Journal of Verbal Learning and Behavior 18:481-496.
  122. Angus B. Grieve-Smith. 1999. English to American Sign Language Machine Translation of Weather Reports. In D. Nordquist (ed.) Proceedings of the Second High Desert Student Conference in Lin- guistics (HDSL2), Albuquerque, NM., pp.23-30.
  123. Mary Hearne and Andy Way. 2003. Seeing the Wood for the Trees: Data-Oriented Translation. In MT Summit IX, New Orleans, LA., pp.165-172.
  124. Judith Holt. 1991. Demographic, Stanford Achieve- ment Test -8th Edition for Deaf and Hard of Hearing Students: Reading Comprehension Sub- group Results.
  125. Matt Huenerfauth. 2004. Spatial and Planning Models of ASL Classifier Predicates for Machine Translation. In The 10th International Confer- ence on Theoretical and Methodological Issues in Machine Translation (TMI 2004) Baltimore, MD., pp.65-74
  126. Matt Huenerfauth. 2005. American Sign Language Generation: Multimodal NLG with Multiple Lin- guistic Channels. In Proceedings of the ACL Stu- dent Research Workshop (ACL 2005) Ann Arbor, MI., pp.37-42
  127. Thomas E. Jerde, John F. Soechting and Martha Flanders. 2003. Coarticulation in Fluent Finger- spelling. Journal of Neuroscience 23(6):2383- 2393.
  128. Ian Marshall and Éva Sáfár. 2002. Sign Lan- guage Generation using HPSG. In Proceedings of the 9th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-02), Keihanna, Japan, pp.105-114.
  129. Makoto Nagao. 1984. A Framework of a Mechani- cal Translation between Japanese and English by Analogy Principle. In A. Elithorn and R. Banerji (eds.) Artificial and Human Intelligence, North- Holland, Amsterdam, The Netherlands, pp.173- 180.
  130. Dónall Ó'Baoill and Patrick A. Matthews. 2000. The Irish Deaf Community (Volume 2): The Structure of Irish Sign Language. The Linguistics Institute of Ireland, Dublin, Ireland. Éva Sáfár and Ian Marshall. 2002. The Architec- ture of an English-Text-to-Sign-Languages Trans- lation System. In Proceedings of Recent Ad- vances in Natural Language Processing (RANLP- 01), Tzigov Chark, Bulgaria, pp.223-228.
  131. Lynette Van Zijl and Dean Barker. 2003. South African Sign Language Machine Translation Sys- tem. In Proceedings of the Second International Conference on Computer Graphics, Virtual Real- ity, Visualisation and Interaction in Africa (ACM SIGGRAPH), Cape Town, South Africa, pp.49- 52. Tony Veale, Alan Conway, and Bróna Collins. 2000. The Challenges of Cross-Modal Translation: Eng- lish to Sign Language Translation in the Zardoz System. Machine Translation 13(1):81-106.
  132. Hideo Watanabe, Sadao Kurohashi and Eiji Ara- maki. 2003. Finding Translation Patterns from Paired Source and Target Dependency Structures. In M. Carl & A. Way (eds.) Recent Advances in Example-Based Machine Translation, Kluwer Academic Publishers, Dordrecht, The Nether- lands, pp.397-420.
  133. Andy Way and Nano Gough. 2003. Developing and Validating an EBMT System using the World Wide Web. Computational Linguistics 29(3):421- 457. Liwei Zhao, Karin Kipper, William Schuler, Chris- tian Vogler, Norman Badler, and Martha Palmer. 2000. A Machine Translation System from Eng- lish to American Sign Language. In Envision- ing Machine Translation in the Information Fu- ture: Proceedings of the Fourth Conference of the Association for Machine Translation (AMTA-00), Cuernavaca, Mexico, pp.293-300.
  134. References P. Brown, S. Della Pietra, V. Della Pietra, and R. Mercer. 1993. The mathematics of statis- tical machine translation: Parameter estima- tion. Computational Linguistics, 19(2):263- 311. S. Corston-Oliver, M. Gamon, and C. Brockett. 2001. A machine learning approach to the the automatic evaluation of machine trans- lation. In Proc. of 39th ACL, pages 148-155, Toulouse, France.
  135. Fujitsu. 2003. ATLAS Honyaku Superpack V9. http://software.fujitsu.com/jp/atlas.
  136. U. Germann, M. Jahr, K. Knight, D. Marcu, and K. Yamada. 2001. Fast decoding and optimal decoding for machine translation. In Proc. of 39th ACL, pages 228-235, Toulouse, France.
  137. K. Imamura. 2002. Application of translation knowledge acquired by hierarchical phrase alignment for pattern-based MT. In Proc. of 9th TMI, pages 74-84, Kyoto, Japan.
  138. G. Kikui, E. Sumita, T. Takezawa, and S. Yamamoto. 2003. Creating corpora for speech-to-speech translation. In Proc. of the EUROSPEECH03, pages 381-384, Geneve, Switzerland.
  139. LogoVista. 2001. X PRO Multilingual Edition Ver.2.0. http://www.logovista.co.jp.
  140. D. Marcu. 2001. Towards a unified approach to memory-and statistical-based machine trans- lation. In Proc. of the 39th ACL, pages 378- 385, Toulouse, France.
  141. S. Ohno and M. Hamanishi. 1984. Ruigo-Shin- Jiten. Kadokawa.
  142. M. Paul, E. Sumita, and S. Yamamoto. 2004. Example-based rescoring of statistical ma- chine translation output. In Proc of the HLT- NAACL, Companion Volume, pages 9-12, Boston, USA.
  143. C.B. Quirk. 2004. Training a sentence-level machine translation confidence measure. In Proc. of 4th LREC, pages 825-828, Lisbon, Portugal. Rulequest. 2004. Data mining tool c5.0. http:/ /rulequest.com/see5-info.html.
  144. K. Su, M. Wu, and J. Chang. 1992. A new quantitative quality measure for machine translation systems. In Proc. of the 14th COLING, pages 433-439, Nantes, France.
  145. E. Sumita, S. Yamada, K. Yamamoto, M. Paul, H. Kashioka, K. Ishikawa, and S. Shi- rai. 1999. Solutions to problems inherent in spoken-language translation: The ATR- MATRIX approach. In Proc. of the Machine Translation Summit VII, pages 229-235, Sin- gapore.
  146. E. Sumita. 2001. Example-based machine translation using DP-matching between word sequences. In Proc. of the 39th ACL, Work- shop: Data-Driven Methods in Machine Translation, pages 1-8, Toulouse, France.
  147. T. Takezawa, E. Sumita, F. Sugaya, H. Ya- mamoto, and S. Yamamoto. 2002. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world. In Proc. of the 3rd LREC, pages 147- 152, Las Palmas, Spain.
  148. C. Tillmann and H. Ney. 2000. Word re- ordering and dp-based search in statistical machine translation. In Proc. of COLING 2000, Saarbruecken, Germany.
  149. Toshiba. 2003. TheHonyaku Ver.7.0. http://pf .toshiba-sol.co.jp/prod/hon yaku/index j.htm.
  150. R.W. Wagner. 1974. The string-to-string correction problem. Journal of the ACM, 21(1):169-173.
  151. Y. Wang and A. Waibel. 1997. Decoding al- gorithm in statistical machine translation. In Proc. of 36th ACL, Madrid, Spain.
  152. T. Watanabe and E. Sumita. 2003. Example- based decoding for statistical machine trans- lation. In Proc. of the Machine Translation Summit IX, pages 410-417, New Orleans, USA. References R.M.K. Sinha. 2002. Translating News Headings from English to Hindi. In "The 6th IASTED International Conference on Artificial Intelligence and Soft Computing (ASC2002) Proceedings", Banff, Canada.
  153. D. Rao, and K. Mohanraj et al. 2000. A Practical Framework For Syntactic Transfer Of Compound -Complex Sentences For English - Hindi Machine Translation. In "International Conference KBCS-2000 Proceedings", Mumbai, India : 343-354.
  154. S. Bandyopadhyay & D. Saha. 2002. Anaphora / Coreference in Machine Translation of News Headlines. In "Discourse Anaphora and Anaphora Resolution Colloquium (DAARC) 2002 Proceedings", Portugal.
  155. S. Bandyopadhyay. 2000a. An Example Based MT System in News Items Domain from English to Indian Languages. In "Machine Translation and Multilingual Applications in the New Millennium Proceedings", Exeter, UK : 10-1 - 10-5.
  156. S. Bandyopadhyay. 2000b. ANUBAAD - Translating News Items from English to Bengali. In "International Conference KBCS2000 Proceedings", Mumbai, India : 297-307.
  157. J. Hutchins. 1999. The Development & Use of Machine Translation Systems and Computer- based translation tools. "The International Symposium on Machine Translation and Computer Language Information Processing Proceeding", China.
  158. T. Yoshimi. 2001. Improvement of Translation Quality of English Newspaper Headlines by Automatic Pre-editing. Journal of Machine Translation, 16(4): 233-250.
  159. C. Kim, M. Hong, Y. Huang, Y. Kim, S. Yang, Y. Seo and S. Choi. 2002. Korean-Chinese Machine Translation Based on Verb Patterns. Lecture Notes in Computer Science, Volume 2499: 94- 103. Kenji Ono. 2003. Translation of News Headline. In "MT SUMMIT IX Proceedings", New Orleans, Louisiana, USA.
  160. Sudip Naskar and Sivaji Bandyopadhyay. 2005. A Phrasal EBMT System for translating English to Bengali. MT SUMMIT X, Phuket, Thailand.
  161. References T. Badia, G. Boleda, M. Melero, A. Oliver. 2005. An n-gram approach to exploiting a monolin- gual corpus for Machine Translation. In Pro- ceedings EBMT Workshop 2005 -this volume.
  162. G. Booij and A. van Santen. 1995. Morfologie. De woordstructuur van het Nederlands. Amster- dam University Press, Amsterdam.
  163. T. Brants. 2001. TnT -A Statistical Part- of-Speech Tagger. Published online at http://www.coli.uni-sb.de/thorsten/tnt.
  164. R.D. Brown. 1996. Example-Based Machine Translation in the Pangloss System. COLING 1996, Copenhagen, Danmark. pp. 169-174.
  165. M. Carl, P. Schmidt and J. Schütz. 2005. Re- versible Template-based Shake & Bake Gen- eration. In Proceedings EBMT Workshop 2005 -this volume.
  166. P. Dirix. 2002a. The METIS Project: Lexical Re- sources. Internship Report, KULeuven.
  167. P. Dirix, 2002b. The METIS Project: Tag-mapping rules. Paper, KULeuven.
  168. P. Dirix, I. Schuurman, V. Vandeghinste. 2005. METIS: Example-Based Machine Translation Using Monolingual Corpora -System Descrip- tion. In Proceedings EBMT Workshop 2005 - this volume.
  169. Y. Dologlou, S. Markantonatou, G. Tambouratzis, O. Yannoutsou, A. Fourla, and N. Ioannou. 2003. Using Monolingual Corpora for Statis- tical Machine Translation: The METIS Sys- tem. In Proceedings of EAMT -CLAW 2003, Dublin, pp. 61-68.
  170. G. Grefenstette. 1999. The World Wide Web as a Resource for Example-Based Machine Trans- lation Tasks. ASLIB, Translating and the Com- puter 21. London.
  171. S. Markantonatou, S. Sofianopoulos, V. Spilioti, Y. Tambouratzkis, M. Vassiliou, O. Yannoutsou, N. Ioannou. 2005. Monolingual Corpus-based MT using Chunks. In Proceedings EBMT Workshop 2005 -this volume.
  172. S. Nirenburg, S. Beale, and C. Domashnev. 1994. A Full-Text Experiment in Example-Based Machine Translation. In Proceedings of the Int. Conf. on New Methods in Language Pro- cessing. Manchester, UK. pp. 78-87.
  173. N. Oostdijk, W. Goedertier, F. Van Eynde, L. Boves, J.P. Martens, M. Moortgat, and H. Baayen. 2002. Experiences from the Spo- ken Dutch Corpus Project. In Proceedings of LREC 2002, vol. 1, pp. 340-347.
  174. K. Papineni, S. Roukos, T. Ward, and W. Zhu. 2002. BLEU: a Method for Automatic Eval- uation of Machine Translation. In Proceedings of the 40st Annual Meeting of the Association for Computational Linguistics.
  175. R. Piepenbrock. 2004. CGN Lexion v.9.3. Spoken Dutch Corpus.
  176. S. Sato. 1993. Example-Based Translation of Technical Terms. Proceedings of TMI 1993. Kyoto, Japan.
  177. V. Vandeghinste. 2002. Maximizing Lexical Coverage in Speech Recognition through Au- tomated Compounding. In Proceedings of LREC2004. ELRA. Paris.
  178. V. Vandeghinste and Y. Pan. 2004. Sentence Com- pression for Automated Subtitling. A Hybrid Approach. In Proceedings of ACL-workshop on Text Summarization. Barcelona.
  179. V. Vandeghinste and E. Tjong Kim Sang. 2004. Using a Parallel Transcript/Subtitle Corpus for Sentence Compression. In Proceedings of LREC2004. ELRA. Paris.
  180. F. Van Eynde. 2004. Tagging and Lemmatisation for the Spoken Dutch Corpus. Internal report.
  181. T. Veale and A. Way. 1997. Gaijin: A Bootstrap- ping, Template-Driven Approach to Example- Based MT. In Proc. of the 2nd Int. Conf. on Recent Advances in NLP. Tzigov Chark, Bul- garia. pp. 239-244.
  182. P. Vossen, L. Bloksma, and P. Boersma. 1999. The Dutch WordNet. University of Amsterdam.
  183. L. Wall. 2004. Perl 5.8.5. http://www.perl.com.
  184. A. Way and N. Gough. 2003. wEBMT: Develop- ing and Validating an Example-Based Machine Translation System using the World Wide Web. Computational Linguistics, 29 (3), pp. 421- 457.

Related papers

Points for the design of hybrid (rule-based and corpus-based) MT systems
Spiros Doikas

The purpose of this paper is to trace the recent developments in corpus linguistics and to evaluate their importance with respect to NLP in general and MT in particular. Consequently, the focus will be on what has been achieved and what is hoped to be achieved in the future in Example-based Machine Translation (EBMT) and Statistics-based Machine Translation (SBMT). It will be demonstrated that these new corpus-related approaches have circumvented many difficulties encountered by the more traditional approach of rule-based machine translation (RBMT). As a result of this, a brighter future to MT can be envisaged with the possibility of hybridisation, as rule-based components will gradually be incorporated to corpus-based systems; thus, imparting the positive knowledge hitherto achieved by forty years or so of painstaking research in RBMT. A Dissertation submitted to the University of Manchester Institute of Science and Technology for the degree of MSc in Machine Translation (1999).

View PDFchevron_right
EBMT by Tree-Phrasing: a Pilot Study
Claude Coulombe

We present a study we conducted to build a repository storing associations between simple dependency treelets in a source language and their corresponding phrases in a target language. To assess the impact of this resource in EBMT, we used the repository to compute coverage statistics on a test bitext and on a nbest list of translation candidates produced by a standard phrase-based decoder.

View PDFchevron_right
Recent Advances in Example-Based Machine Translation
Michael Carl

2003

Recent Advances in Example-Based Machine Translation is of relevance to researchers and program developers in the field of Machine Translation and especially Example-Based Machine Translation, bilingual text processing and cross-linguistic information retrieval. It is also of interest to translation technologists and localisation professionals. Recent Advances in Example-Based Machine Translation fills a void, because it is the first book to tackle the issue of EBMT in depth. It gives a state-of-the-art overview of EBMT techniques and provides a coherent structure in which all aspects of EBMT are embedded. Its contributions are written by long-standing researchers in the field of MT in general, and EBMT in particular. This book can be used in graduate-level courses in machine translation and statistical NLP.

View PDFchevron_right
Hybridity in MT: Experiments on the Europarl corpus
Declan Groves

2006

demonstrate that their Marker-based EBMT system is capable of outperforming a word-based SMT system trained on reasonably large data sets. 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.

View PDFchevron_right
Compiling and using a shareable parallel corpus for MT evaluation
Eric S Atwell

2004

Parallel texts are an important resource for applications in multilingual natural language processing and human language technology. This paper presents a method for exploiting available parallel texts, both human translated and revised machine translated texts in order to populate machine translation and translation memory databases.

View PDFchevron_right

Related topics

  • Machine Translation
  • Source Language
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved