QUALESEstimación Automática de Calidad de Traducción Mediante Aprendizaje Automático Supervisado y No-Supervisado

  1. Calonge, Eusebi
  2. Martin, Maite
  3. Etchegoyhen, Thierry
  4. Martínez Garcia, Eva
  5. Azpeitia, Andoni
  6. Alegría Loinaz, Iñaki
  7. Labaka Intxauspe, Gorka
  8. Otegi, Arantza
  9. Sarasola Gabiola, Kepa
  10. Cortés Etxabe, Itziar
  11. Jauregi Carrera, Amaia
  12. Ellakuria, Igor
Journal:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Year of publication: 2018

Issue: 61

Pages: 143-146

Type: Article

More publications in: Procesamiento del lenguaje natural

Abstract

The automatic quality estimation (QE) of machine translation consists in measuring the quality of translations without access to human references, usually via machine learning approaches. A good QE system can help in three aspects of translation processes involving machine translation and post-editing: increasing productivity (by ruling out poor quality machine translation), estimating costs (by helping to forecast the cost of post-editing) and selecting a provider (if several machine translation systems are available). Interest in this research area has grown significantly in recent years, leading to regular shared tasks in the main machine translation conferences and intense scientific activity. In this article we review the state of the art in this research area and present project QUALES, which is under development.

Bibliographic References

  • Blatz, J. et al. 2004. Confidence estimation for machine translation. En Proceedings of COLING, páginas 315-321.
  • Bojar, O. et al. 2017. Findings of the 2017 conference on machine translation. En Proceedings of the Second Conference on Machine Translation, páginas 169-214, Copenhagen, Denmark.
  • Callison-Burch, C. et al. 2012. Findings of the 2012 Workshop on Statistical Machine Translation. En Proceedings of the Seventh Workshop on Statistical Machine Translation.
  • Kim, H., J.-H. Lee, y S.-H. Na. 2017. Predictor-estimator using multilevel task learning with stack propagation for neural quality estimation. En Proceedings of the Second Conference on Machine Translation, páginas 562-568, Copenhagen, Denmark.
  • Martins, A. F. T., F. Kepler, y J. Monteiro. 2017. Unbabel's participation in the wmt17 translation quality estimation shared task. En Proceedings of the Second Conference on Machine Translation, páginas 569-574, Copenhagen, Denmark.
  • Moreau, E. y C. Vogel. 2012. Quality estimation: an experimental study using unsupervised similarity measures. En Proceedings of the Seventh Workshop on Statistical Machine Translation, páginas 120-126.
  • Popovic, M. 2012. Morpheme- and posbased IBM1 and language model scores for translation quality estimation. En Proceedings of the Seventh Workshop on Statistical Machine Translation, páginas 133-137.
  • Quirk, C. 2004. Training a sentence-level machine translation confidence measure. En Proceedings of LREC, páginas 825-828.
  • Shah, K. et al. 2016. SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features. En Proceedings of the First Conference on Machine Translation, volumen 2, páginas 838-842.
  • Specia, L. et al. 2009. Estimating the sentence-level quality of machine translation systems. En 13th Conference of the European Association for Machine Translation, páginas 28-37.
  • Specia, L., G. Paetzold, y C. Scarton. 2015. Multi-level translation quality prediction with QUEST++. Proceedings of ACL-IJCNLP 2015 System Demonstrations, páginas 115-120.
  • Specia, L., D. Raj, y M. Turchi. 2010. Machine translation evaluation versus quality estimation. Machine Translation, 24(1):39-50.