Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction to Computer-Assisted Translation
Statistical Framework
Statistical Machine Translation
Statistical and Finite-State Models
Statistical Alignment Models
Experimental Framework
Results
Results with N-Best Hypotheses
References
All Topics
Psychology
Cognitive Science

Statistical Approaches to Computer-Assisted Translation

Profile image of Nei OliverNei Oliver

2009, Computational Linguistics

Abstract

Universitat Jaume I Current machine translation (MT) systems are still not perfect. In practice, the output from these systems needs to be edited to correct errors. A way of increasing the productivity of the whole translation process (MT plus human work) is to incorporate the human correction activities within the translation process itself, thereby shifting the MT paradigm to that of computer-assisted translation. This model entails an iterative process in which the human translator activity is included in the loop: In each iteration, a prefix of the translation is validated (accepted or amended) by the human and the system computes its best (or n-best) translation suffix hypothesis to complete this prefix. A successful framework for MT is the so-called statistical (or pattern recognition) framework. Interestingly, within this framework, the adaptation of MT systems to the interactive scenario affects mainly the search process, allowing a great reuse of successful techniques and models. In this article, alignment templates, phrase-based models, and stochastic finite-state transducers are used to develop computer-assisted translation systems. These systems were assessed in a European project (TransType2) in two real tasks: The translation of printer manuals; manuals and the translation of the Bulletin of the European Union. In each task, the following three pairs of languages were involved (in both translation directions):

Related papers

A weighted finite state transducer translation template model for statistical machine translation
Shankar Kumar

Natural Language Engineering, 2005

We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. This is a source-channel model of translation inspired by the Alignment Template translation model. The model attempts to overcome the deficiencies of word-to-word translation models by considering phrases rather than words as units of translation. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard finite state machine operations involving these transducers. One of the benefits of using this framework is that it avoids the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We report and analyze bitext word alignment and translation performance on the Hansards French-English task and the FB...

View PDFchevron_right
A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation
shankar kumar

2003

We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard FSM operations involving these transducers. One of the benefits of using this framework is that it obviates the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We evaluate the implementation of the model on the Frenchto-English Hansards task and report alignment and translation performance.

View PDFchevron_right
The ITI statistical machine translation system
Juan Vilar

2006

One of the translation systems currently under development at ITI uses a phrase based approach: translations are produced considering sequences of words as the elementary unit. We discuss here the implications of monotonicity and non-monotonicity assumptions and their relation with the search algorithms. Also different criteria for the selection of segments and training of parameters are discussed and experimentally tested.

View PDFchevron_right
Proceedings of the Fourth Workshop on Statistical Machine Translation - StatMT '09
Eric Wehrli

2009

This paper presents the results of the WMT09 shared tasks, which included a translation task, a system combination task, and an evaluation task. We conducted a large-scale manual evaluation of 87 machine translation systems and 22 system combination entries. We used the ranking of these systems to measure how strongly automatic metrics correlate with human judgments of translation quality, for more than 20 metrics. We present a new evaluation technique whereby system output is edited and judged for correctness. 2.1 Test data The test data for this year's task was created by hiring people to translate news articles that were drawn from a variety of sources during the period from the end of September to mid-October of 2008. A total of 136 articles were selected, in roughly equal amounts from a variety of Czech, English, French, German, Hungarian, Italian and Spanish news sites: 2

View PDFchevron_right
Analysis and System Combination of Phrase and N-Gram-Based Statistical Machine Translation Systems
Marta Costa-jussa

2007

In the framework of the Tc-Star project, we analyze and propose a combination of two Statistical Machine Translation systems: a phrase-based and an N -gram-based one. The exhaustive analysis includes a comparison of the translation models in terms of efficiency (number of translation units used in the search and computational time) and an examination of the errors in each system's output. Additionally, we combine both systems, showing accuracy improvements.

View PDFchevron_right
Statistical methods for machine translation
Stephan Vogel

2000

Abstract. In this article we describe the statistical approach to machine translation as implemented in the stattrans module of the Verbmobil system. The statistical translation approach uses two types of information: a translation model and a language model. The language model used is an m-gram model. The translation model comprises a stochastic lexicon and word position parameters. To capture dependencies between word groups in each of the two languages, alignment templates are used.

View PDFchevron_right
The University of Maryland Statistical Machine Translation System for the Fourth Workshop on Machine Translation
hendra setiawan

2009

This paper describes the techniques we explored to improve the translation of news text in the German-English and Hungarian-English tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and incorporation of a feature scoring the alignment of function words in the hypothesized translation. We also explored the use of monolingual paraphrases to improve coverage, as well as co-training to improve the quality of the segmentation lattices used, but these did not lead to improvements.

View PDFchevron_right

References (45)

  1. Amengual, J. C., J. M. Benedí, A. Casta ño, A. Castellanos, V. M. Jiménez, D. Llorens, A. Marzal, M. Pastor, F. Prat, E. Vidal, and J. M. Vilar. 2000. The EuTrans-I speech translation system. Machine Translation, 15:75-103.
  2. Amengual, J. C. and E. Vidal. 1998. Efficient error-correcting Viterbi parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(10):1109-1116.
  3. Bender, O., S. Hasan, D. Vilar, R. Zens, and H. Ney. 2005. Comparison of generation strategies for interactive machine translation. In Proceedings of the 10th Annual Conference of the European Association for Machine Translation (EAMT 05), pages 33-40, Budapest.
  4. Berger, A. L., P. F. Brown, S. A. Della Pietra, V. J. Della Pietra, J. R. Gillett, A. S. Kehler, and R. L. Mercer. 1996. Language translation apparatus and method of using context-based translation models. United States Patent No. 5510981, April.
  5. Berstel, J. 1979. Transductions and Context-Free Languages. B. G. Teubner, Stuttgart.
  6. Bisani, M. and H. Ney. 2004. Bootstrap estimates for confidence intervals in ASR performance evaluation. In Proceedings of the International Conference on Acoustic, Speech and Signal Processing (ICASSP 04), volume 1, pages 409-412, Montreal.
  7. Bowker, L. 2002. Computer-Aided Translation Technology: A Practical Introduction, chapter 5: Translation-memory systems. Didactics of Translation. University of Ottawa Press, pages 92-127.
  8. Brown, P. F., J. Cocke, S. A. Della Pietra, V. J. Della Pietra, F. Jelinek, J. D. Lafferty, R. L. Mercer, and P. S. Roosin. 1990. A statistical approach to machine translation. Computational Linguistics, 16(2):79-85.
  9. Brown, P. F., S. A. Della Pietra, V. J. Della Pietra, and R. L. Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2):263-310.
  10. Callison-Burch, C., M. Osborne, and P. Koehn. 2006. Re-evaluating the role of BLEU in machine translation research. In Proceedings of the 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL 06), pages 249-256, Trento.
  11. Casacuberta, F., H. Ney, F. J. Och, E. Vidal, J. M. Vilar, S. Barrachina, I. García-Varea, D. Llorens, C. Martínez, S. Molau, F. Nevado, M. Pastor, D. Pic ó, A. Sanchis, and C. Tillmann. 2004a. Some approaches to statistical and finite-state speech-to-speech translation. Computer Speech and Language, 18:25-47.
  12. Casacuberta, F. and E. Vidal. 2004. Machine translation with inferred stochastic finite-state transducers. Computational Linguistics, 30(2):205-225.
  13. Casacuberta, F. and E. Vidal. 2007. Learning finite-state models for machine translation. Machine Learning, 66(1):69-91.
  14. Casacuberta, F., E. Vidal, and D. Pic ó. 2005. Inference of finite-state transducers from regular languages. Pattern Recognition, 38:1431-1443.
  15. Casacuberta, F., E. Vidal, A. Sanchis, and J. M. Vilar. 2004b. Pattern recognition approaches for speech-to-speech translation. Cybernetic and Systems: an International Journal, 35(1):3-17.
  16. Civera, J., J. M. Vilar, E. Cubel, A. L. Lagarda, S. Barrachina, E. Vidal, F. Casacuberta, D. Pic ó, and J. González. 2004a. From machine translation to computer assisted translation using finite-state models. In Proceedings of the Conference on Empirical Methods for Natural Language Processing (EMNLP 04), pages 349-356, Barcelona.
  17. Civera, J., J. M. Vilar, E. Cubel, A. L. Lagarda, S. Barrachina, F. Casacuberta, E. Vidal, D. Pic ó, and J. González. 2004b. A syntactic pattern recognition approach to computer assisted translation. In Advances in Statistical, Structural and Syntactical Pattern Recognition, Proceedings of the Joint IAPR International Workshops on Syntactical and Structural Pattern Recognition (SSPR 04) and Statistical Pattern Recognition (SPR 04)), Lisbon, Portugal, August 18-20, volume 3138 of Lecture Notes in Computer Science. Springer-Verlag, Heidelberg, pages 207-215.
  18. Cubel, E., J. Civera, J. M. Vilar, A. L. Lagarda, S. Barrachina, E. Vidal, F. Casacuberta, D. Pic ó, J. González, and L. Rodríguez. 2004. Finite-state models for computer assisted translation. In Proceedings of the 16th European Conference on Artificial Intelligence (ECAI 04), pages 586-590, Valencia.
  19. Cubel, E., J. González, A. Lagarda, F. Casacuberta, A. Juan, and E. Vidal. 2003. Adapting finite-state translation to the TransType2 project. In Proceedings of the Joint Conference Combining the 8th International Workshop of the European Association for Machine Translation and the 4th Controlled Language Applications Workshop 03), pages 54-60, Dublin.
  20. Foster, G. 2002. Text Prediction for Translators. Ph.D. thesis, Université de Montréal, Canada.
  21. Foster, G., P. Isabelle, and P. Plamondon. 1997. Target-text mediated interactive machine translation. Machine Translation, 12(1-2):175-194.
  22. Isabelle, P. and K. Church. 1997. Special issue on new tools for human translators. Machine Translation, 12(1-2).
  23. Jelinek, F. 1998. Statistical Methods for Speech Recognition. The MIT Press, Cambridge, MA. Jiménez, V. M. and A. Marzal. 1999. Computing the k shortest paths: a new algorithm and an experimental comparison. In Algorithm Engineering: Proceedings of the 3rd International Workshop (WAE 99), London, UK, July 19-21, volume 1668 of Lecture Notes in Computer Science. Springer-Verlag, Heidelberg, pages 15-29.
  24. Kay, M. 1997. The proper place of men and machines in language translation. Machine Translation, 12:3-23. [This article first appeared as a Xerox PARC Working Paper in 1980].
  25. Khadivi, S. and C. Goutte. 2003. Tools for corpus alignment and evaluation of the alignments (deliverable d4.9). Technical report, TransType2 (IST-2001-32091).
  26. Khadivi, S., R. Zens, and H. Ney. 2006. Integration of speech to computer-assisted translation using finite-state automata. In Proceedings of the 44th Annual Meeting of the Association for Computational Linguistics and 21th International Conference on Computational Linguistics (COLING/ACL 06), pages 467-474, Sydney.
  27. Khadivi, S., A. Zolnay, and H. Ney. 2005. Automatic text dictation in computer-assisted translation. In Proceedings of the European Conference on Speech Communication and Technology, (INTERSPEECH 05-EUROSPEECH), pages 2265-2268, Lisbon.
  28. Koehn, P. 2004. Statistical significance tests for machine translation evaluation. In Proceedings of the Conference on Empirical Methods for Natural Language Processing (EMNLP 04), pages 388-395, Barcelona.
  29. Koehn, P., F. J. Och, and D. Marcu. 2003. Statistical phrase-based translation. In Proceedings of the 2003 Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL 03), pages 127-133, Edmonton.
  30. Langlais, P., G. Foster, and G. Lapalme. 2000. TransType: a computer-aided translation typing system. In Proceedings of the NAACL/ANLP Workshop on Embedded Machine Translation Systems, pages 46-52, Seattle, WA.
  31. Langlais, P., G. Lapalme, and M. Loranger. 2002. Transtype: Development-evaluation cycles to boost translator's productivity. Machine Translation, 15(4):77-98.
  32. Macklovitch, E. 2006. TransType2: The last word. In Proceedings of the 5th International Conference on Languages Resources and Evaluation (LREC 06), pages 167-172, Genoa.
  33. Macklovitch, E., N. T. Nguyen, and R. Silva. 2005. User evaluation report. Technical report, TransType2 (IST-2001-32091).
  34. Marcu, D. and W. Wong. 2002. A phrase-based, joint probability model for statistical machine translation. In Proceedings of the Conference on Empirical Methods for Natural Language Processing (EMNLP 02), pages 133-139, Philadelphia, PA.
  35. Ney, H., S. Nießen, F. Och, H. Sawaf, C. Tillmann, and S. Vogel. 2000. Algorithms for statistical translation of spoken language. IEEE Transactions on Speech and Audio Processing, 8(1):24-36.
  36. Och, F. J. 1999. An efficient method for determining bilingual word classes. In Proceedings of the 9th Conference of the European Chapter of the Association for
  37. Vidal, E. and F. Casacuberta. 2004. Learning finite-state models for machine translation. In Grammatical Inference: Algorithms and Applications, Proceedings of the 7th International Coloquium on Grammatical Inference (ICGI 04), Athens, Greece, October 11-13, volume 3264 of Lecture Notes in Artificial Intelligence. Springer, Heidelberg, pages 16-27.
  38. Vidal, E., F. Casacuberta, L. Rodríguez, J. Civera, and C. Martínez. 2006. Computer-assisted translation using speech recognition. IEEE Transactions on Speech and Audio Processing, 14(3):941-951.
  39. Vidal, E., F. Thollard, F. Casacuberta C. de la Higuera, and R. Carrasco. 2005. Probabilistic finite-state machines- part II. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(7):1025-1039.
  40. Whitelock, P. J., M. McGee Wood, B. J. Chandler, N. Holden, and H. J. Horsfall. 1986. Strategies for interactive machine translation: The experience and implications of the UMIST Japanese project. In Proceedings of the 11th International Conference on Computational Linguistics (COLING 86), pages 329-334, Bonn.
  41. Yamron, J., J. Baker, P. Bamberg, H. Chevalier, T. Dietzel, J. Elder, F. Kampmann, M. Mandel, L. Manganaro, T. Margolis, and E. Steele. 1993. LINGSTAT: an interactive, machine-aided translation system. In Proceedings of the Workshop on Human Language Technology, pages 191-195, Princeton, NJ.
  42. Zajac, R. 1988. Interactive translation: A new approach. In Proceedings of the 12th International Conference on Computational Linguistics (COLING 88), pages 785-790, Budapest.
  43. Zens, R. and H. Ney. 2004. Improvements in phrase-based statistical machine translation. In Proceedings of the Human Language Technology Conference / North American Chapter of the Association for Computational Linguistics Annual Meeting (HLT-NAACL 04), pages 257-264, Boston, MA.
  44. Zens, R., F. J. Och, and H. Ney. 2002. Phrase-based statistical machine translation. In Advances in Artificial Intelligence. 25th Annual German Conference on Artificial Intelligence (KI 02), Aachen, Germany, September 16-22, Proceedings, volume 2479 of Lecture Notes on Artificial Intelligence. Springer Verlag, Heidelberg, pages 18-32.
  45. Zhang, Y. and S. Vogel. 2004. Measuring confidence intervals for the machine translation evaluation metrics. In Proceedings of the Tenth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI 04), pages 294-301, Baltimore, MD.

Related papers

Finite-state models for computer assisted translation
David Picó Vila, Juan Vilar, Antonio Lagarda

2004

Current methodologies for automatic translation cannot be expected to produce high quality translations. However, some techniques based on these methodologies can increase the productivity of human translators. The basis of one of these methodologies are finite-state transducers, which are adequate models for computer assisted translation. These models have proved its efficiency in many pattern recognition and artificial intelligence tasks such as speech recognition, handwriting recognition and machine translation for specific domains.

View PDFchevron_right
From machine translation to computer assisted translation using finite-state models
Sergio Barrachina, David Picó Vila, Juan Vilar, Antonio Lagarda

2004

State-of-the-art machine translation techniques are still far from producing high quality translations. This drawback leads us to introduce an alternative approach to the translation problem that brings human expertise into the machine translation scenario. In this framework, namely Computer Assisted Translation (CAT), human translators interact with a translation system, as an assistance tool, that dinamically offers, a list of translations that best completes the part of the sentence already translated. In this paper, finite state transducers are presented as a candidate technology in the CAT paradigm. The appropriateness of this technique is evaluated on a printer manual corpus and results from preliminary experiments confirm that human translators would reduce to less than 25% the amount of work to be done for the same task.

View PDFchevron_right
Computer-assisted translation using finite-state transducers
Juan Vilar, Antonio Lagarda

2005

Resumen: Traducción asistida por ordenador (CAT) es una aproximación alternativa a la traducción automática que integra el conocimiento humano en el proceso de la traducción automática. En este marco, un traductor interactúa con un sistema de traducción que dinámicamente ofrece una lista de traducciones que mejor completan la parte de oración ya traducida. La tecnología de transductores estocásticos de estados finitos se propone para dar apoyo a este sistema CAT. Este sistema fue evaluado en dos tareas reales de diferente complejidad en varias lenguas. Palabras clave: traducción automática, traducción asistida por ordenador, transductores estocásticos de estados finitos Abstract: Computer-Assisted Translation (CAT) is an alternative approach to machine translation, that integrates human expertise into the automatic translation process. In this framework, a human translator interacts with a translation system that dynamically offers a list of translations that best completes the part of the sentence already translated. Stochastic finite-state transducer technology is proposed to support this CAT system. The system was assessed on two real tasks of different complexity in several languages.

View PDFchevron_right
A Syntactic Pattern Recognition Approach to Computer Assisted Translation
David Picó Vila

Lecture Notes in Computer Science, 2004

It is a fact that current methodologies for automatic translation cannot be expected to produce high quality translations. An alternative approach is to use them as an aid to manual translation. We focus on a possible way to help human translators: to interactively provide completions for the parts of the sentences already translated. We explain how finite state transducers can be used for this task and show experiments in which the keystrokes needed to translate printer manuals were reduced to nearly 25% of the original.

View PDFchevron_right
The CMU statistical machine translation system
Stephan Vogel

2003

Abstract In this paper we describe the components of our statistical machine translation system. This system combines phrase-tophrase translations extracted from a bilingual corpus using different alignment approaches. Special methods to extract and align named entities are used. We show how a manual lexicon can be incorporated into the statistical system in an optimized way. Experiments on Chinese-to-English and Arabic-to-English translation tasks are presented.

View PDFchevron_right

Related topics

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