Abstract
We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since inappropriate weight estimations lead to a wide variability of translation quality results, reaching a reliable estimate for such weights is critical for machine translation research. For this reason, a variety of methods have been proposed to reach reasonable estimates. In this paper, we present an algorithmic description and empirical results proving that DRR is able to provide comparable translation quality when compared to state-of-the-art estimation methods [i.e. MERT (Och in Proceedings of the annual meeting of the association for computational linguistics, 2003) and MIRA (Cherry and Foster in Proceedings of the North American chapter of the association for computational linguistics, 2012)], with a reduction in computational cost. Moreover, the empirical results reported are coherent across different corpora and language pairs.
Similar content being viewed by others
References
Barrachina S, Bender O, Casacuberta F, Civera J, Cubel E, Khadivi S, Lagarda A, Ney H, Tomás J, Vidal E et al (2009) Statistical approaches to computer-assisted translation. Comput Ling 35(1):3–28
Bojar O, Buck C, Federmann C, Haddow B, Koehn P, Monz C, Post M, Specia L (eds) (2014) Proceedings of the ninth workshop on statistical machine translation. Association for Computational Linguistics
Brown PF, Pietra VJD, Pietra SAD, Mercer RL (1993) The mathematics of statistical machine translation: parameter estimation. Comput Ling 19:263–311
Callison-Burch C, Koehn P, Monz C, Peterson K, Przybocki M, Zaidan OF (2010) Findings of the 2010 joint workshop on statistical machine translation and metrics for machine translation. In: Proceedings of the annual meeting of the association for computational linguistics, pp 17–53
Chen B, Cherry C (2014) A systematic comparison of smoothing techniques for sentence-level bleu. In: Proceedings of the workshop on statistical machine translation, pp 362–367
Cherry C, Foster G (2012) Batch tuning strategies for statistical machine translation. In: Proceedings of the North American chapter of the association for computational linguistics, pp 427–436
Clark JH, Dyer C, Lavie A, Smith NA (2011) Better hypothesis testing for statistical machine translation: controlling for optimizer instability. In: Proceedings of the annual meeting of the association for computational linguistics, pp 176–181
Crammer K, Dekel O, Keshet J, Shalev-Shwartz S, Singer Y (2006) Online passive-aggressive algorithms. J Mach Learn Res 7:551–585
Hasler E, Haddow B, Koehn P (2011) Margin infused relaxed algorithm for moses. Prague Bull Math Ling 96:69–78
Hopkins M, May J (2011) Tuning as ranking. In: Proceedings of the conference on empirical methods in natural language processing, pp 1352–1362
Kneser R, Ney H (1995) Improved backing-off for m-gram language modeling. In: Proceedings of the international conference on acoustics, speech and signal processing, pp 181–184
Koehn P (2005) Europarl: a parallel corpus for statistical machine translation. In: Proceedings of the machine translation summit, pp 79–86
Koehn P (2010) Statistical machine translation. Cambridge University Press, Cambridge
Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: open source toolkit for statistical machine translation. In: Proceedings of the annual meeting of the association for computational linguistics, pp 177–180
Lavie MDA (2014) Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the annual meeting of the association for computational linguistics, pp 376–387
Marie B, Max A (2015) Multi-pass decoding with complex feature guidance for statistical machine translation. In: Proceedings of the annual meeting of the association for computational linguistics, pp 554–559
Martínez-Gómez P, Sanchis-Trilles G, Casacuberta F (2012) Online adaptation strategies for statistical machine translation in post-editing scenarios. Pattern Recogn 45(9):3193–3203
Nakov P, Vogel S (2017) Robust tuning datasets for statistical machine translation. arXiv:1710.00346
Neubig G, Watanabe T (2016) Optimization for statistical machine translation: a survey. Comput Ling 42(1):1–54
Och FJ (2003) Minimum error rate training in statistical machine translation. In: Proceedings of the annual meeting of the association for computational linguistics, pp 160–167
Och FJ, Ney H (2003) A systematic comparison of various statistical alignment models. Comput Ling 29:19–51
Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the international conference on acoustics, speech and signal processing, pp 311–318
Sanchis-Trilles G, Casacuberta F (2010) Log-linear weight optimisation via Bayesian adaptation in statistical machine translation. In: Proceedings of the annual meeting of the association for computational linguistics, pp 1077–1085
Sanchis-Trilles G, Casacuberta F (2015) Improving translation quality stability using Bayesian predictive adaptation. Comput Speech Lang 34(1):1–17
Snover M, Dorr B, Schwartz R, Micciulla L, Makhoul J (2006) A study of translation edit rate with targeted human annotation. In: Proceedings of the annual meeting of the association for machine translation in the Americas, pp 223–231
Sokolov A, Yvon F (2011) Minimum error rate training semiring. In: Proceedings of the annual conference of the European association for machine translation, pp 241–248
Stauffer C, Grimson WEL (2000) Learning patterns of activity using real-time tracking. Pattern Anal Mach Intell 22(8):747–757
Stolcke A (2002) Srilm—an extensible language modeling toolkit. In: Proceedings of the international conference on spoken language processing, pp 901–904
Tiedemann J (2009) News from opus—a collection of multilingual parallel corpora with tools and interfaces. In: Proceedings of the recent advances in natural language processing, pp 237–248
Tiedemann J (2012) Parallel data, tools and interfaces in opus. In: Proceedings of the language resources and evaluation conference, pp 2214–2218
Author information
Authors and Affiliations
Corresponding author
Additional information
The research leading to these results were partially supported by projects CoMUN-HaT-TIN2015-70924-C2-1-R (MINECO/FEDER) and PROMETEO/2018/004. We also acknowledge NVIDIA for the donation of a GPU used in this work.
Rights and permissions
About this article
Cite this article
Chinea-Rios, M., Sanchis-Trilles, G. & Casacuberta, F. Discriminative ridge regression algorithm for adaptation in statistical machine translation. Pattern Anal Applic 22, 1293–1305 (2019). https://doi.org/10.1007/s10044-018-0720-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-018-0720-5