Overcoming statistical machine translation limitations: error analysis and proposed solutions for the Catalan–Spanish language pair
- 271 Downloads
This work aims to improve an N-gram-based statistical machine translation system between the Catalan and Spanish languages, trained with an aligned Spanish–Catalan parallel corpus consisting of 1.7 million sentences taken from El Periódico newspaper. Starting from a linguistic error analysis above this baseline system, orthographic, morphological, lexical, semantic and syntactic problems are approached using a set of techniques. The proposed solutions include the development and application of additional statistical techniques, text pre- and post-processing tasks, and rules based on the use of grammatical categories, as well as lexical categorization. The performance of the improved system is clearly increased, as is shown in both human and automatic evaluations of the system, with a gain of about 1.1 points BLEU observed in the Spanish-to-Catalan direction of translation, and a gain of about 0.5 points in the reverse direction. The final system is freely available online as a linguistic resource.
KeywordsStatistical machine translation N-gram-based translation Linguistic knowledge Grammatical categories
The authors would like to thank TALP Research Center and Barcelona Media Innovation Center for its support and permission to publish this research. We would like to give credit to the anonymous reviewers of this paper for their valuable suggestions. This work has been partially funded by the Spanish Department of Science and Innovation through the Juan de la Cierva fellowship program and the Spanish Government under the BUCEADOR project (TEC2009-14094-C04-01).
- Bangalore, S., & Riccardi, G. (2000). Stochastic finite-state models for spoken language machine translation. In Workshop on Embedded Machine Translation Systems, Seattle, WA.Google Scholar
- Brown, P., della Pietra, S., et al. (1993). The mathematics of statistical machine translation. Computational Linguistics, 19(2), 263–311.Google Scholar
- Carreras, X., Chao, I., et al. (2004). FreeLing: An open-source suite of language analyzers. In Conference on Language Resources and Evaluation, Lisbon, Portugal.Google Scholar
- Crego, J. M., de Gispert, A., et al. (2006). N-gram-based SMT System Enhanced with Reordering. In Human Language Technology Conference (HLT-NAACL’06): Proceedings of the Workshop on Statistical Machine Translation, New York.Google Scholar
- de Gispert, A., & Mariño, J. (2006). Catalan-English statistical machine translation without parallel corpus: Bridging through Spanish. In Proceedings of LREC 5th Workshop on Strategies for developing Machine Translation for Minority Languages (SALTMIL’06). Genova, 65–68.Google Scholar
- Niessen, S., & Ney, H. (2000). Improving SMT quality with morpho-syntactic analysis. In International Conference on Computational Linguistics, Saarbrücken, Germany.Google Scholar
- Och, F. J. (2003). Minimum error rate training in statistical machine translation. In 41st Meeting of the Association for Computational Linguistics, Sapporo, Japan.Google Scholar
- Popović, M., de Gispert, A., et al. (2006). Morpho-syntactic information for automatic error analysis of statistical machine translation output. In HLT/NAACL Workshop on Statistical Machine Translation, New York.Google Scholar
- Popović, M., & Ney, H. (2004). Towards the use of word stems and suffixes for statistical machine translation. In International Conference on Language Resources and Evaluation, Lisbon, Portugal.Google Scholar
- Popović, M., & Ney, H. (2006). POS-based word reorderings for statistical machine translation. In International Conference on Language Resources and Evaluation, Genoa, Italy.Google Scholar