Statistical Machine Translation of German Compound Words
German compound words pose special problems to statistical machine translation systems: the occurence of each of the components in the training data is not sufficient for successful translation. Even if the compound itself has been seen during training, the system may not be capable of translating it properly into two or more words. If German is the target language, the system might generate only separated components or may not be capable of choosing the correct compound. In this work, we investigate and compare different strategies for the treatment of German compound words in statistical machine translation systems. For translation from German, we compare linguistic-based and corpus-based compound splitting. For translation into German, we investigate splitting and rejoining German compounds, as well as joining English potential components. Additionaly, we investigate word alignments enhanced with knowledge about the splitting points of German compounds. The translation quality is consistently improved by all methods for both translation directions.
KeywordsTarget Language Compound Word Training Corpus Translation Direction Statistical Machine Translation
Unable to display preview. Download preview PDF.
- 1.Koehn, P., Knight, K.: Empirical Methods for Compound Splitting. In: Proc. 10th Conf. of the European Chapter of the Association for Computational Linguistics (EACL), Budapest, Hungary, pp. 347–354 (2003)Google Scholar
- 2.Koehn, P., Montz, C.: Shared task: statistical machine translation between European languages. In: Proc. ACL Workshop on Building and Using Parallel Texts, Ann Arbor, Michigan, pp. 119–124 (2005)Google Scholar
- 3.Niessen, S., Ney, H.: Improving SMT quality with morpho-syntactic analysis. In: Proc. 18th Int. Conf. on Computational Linguistics (COLING), Saarbrücken, Germany, pp. 1081–1085 (2000)Google Scholar
- 4.Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proc. 40th Annual Meeting of the Assoc. for Computational Linguistics (ACL), Philadelphia, PA, pp. 311–318 (2002)Google Scholar
- 5.Popović, M., Ney, H.: Improving Word Alignment Quality using Morpho-syntactic Information. In: Proc. 20th Int. Conf. on Computational Linguistics (COLING), Geneva, Switzerland, pp. 310–314 (2004)Google Scholar
- 6.Toutanova, K., Tolga Ilhan, H., Manning, C.: Extensions to HMM-based statistical word alignment models. In: Proc. Conf. on Empirical Methods for Natural Language Processing (EMNLP), Philadelphia, PA, pp. 87–94 (2002)Google Scholar
- 7.Vilar, D., Matusov, E., Hasan, S., Zens, R., Ney, H.: Statistical Machine Translation of European Parliamentary Speeches. In: Proc. MT Summit X, Phuket, Thailand, pp. 259–266 (2005)Google Scholar
- 8.Zens, R., Bender, O., Hasan, S., Khadivi, S., Matusov, E., Xu, J., Zhang, Y., Ney, H.: The RWTH Phrase-based Statistical Machine Translation System. In: Proc. Int. Workshop on Spoken Language Translation (IWSLT), Pittsburgh, PA, pp. 155–162 (2005)Google Scholar