Pivot Language Approach for Phrase-Based Statistical Machine Translation

Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 856–863, Prague, Czech Republic, June 2007. c⃝2007 Association for Computational Linguistics Pivot Language Approach for Phrase-Based Statistical Machine Translation Hua Wu and Haifeng Wang Toshiba (China) Research and Development Center 5/F., Tower W2, Oriental Plaza, No.1, East Chang An Ave., Dong Cheng District Beijing, 100738, China {wuhua,wanghaifeng}@rdc.toshiba.com.cn Abstract This paper proposes a novel method for phrase-based statistical machine translation by using pivot language. To conduct trans- lation between languages Lf and Le with a small bilingual corpus, we bring in a third language Lp, which is named the pivot lan- guage. For Lf-Lp and Lp-Le, there exist large bilingual corpora. Using only Lf-Lp and Lp-Le bilingual corpora, we can build a translation model for Lf-Le. The advantage of this method lies in that we can perform translation between Lf and Le even if there is no bilingual corpus available for this language pair. Using BLEU as a metric, our pivot language method achieves an ab- solute improvement of 0.06 (22.13% rela- tive) as compared with the model directly trained with 5,000 Lf-Le sentence pairs for French-Spanish translation. Moreover, with a small Lf-Le bilingual corpus available, our method can further improve the transla- tion quality by using the additional Lf-Lp and Lp-Le bilingual corpora. 1 Introduction For statistical machine translation (SMT), phrase- based methods (Koehn et al., 2003; Och and Ney, 2004) and syntax-based methods (Wu, 1997; Al- shawi et al. 2000; Yamada and Knignt, 2001; Melamed, 2004; Chiang, 2005; Quick et al., 2005; Mellebeek et al., 2006) outperform word-based methods (Brown et al., 1993). These methods need large bilingual corpora. However, for some lan- guages pairs, only a small bilingual corpus is available, which will degrade the performance of statistical translation systems. To solve this problem, this paper proposes a novel method for phrase-based SMT by using a pivot language. To perform translation between languages Lf and Le, we bring in a pivot language Lp, for which there exist large bilingual corpora for language pairs Lf-Lp and Lp-Le. With the Lf-Lp and Lp-Le bilingual corpora, we can build a translation model for Lf-Le by using Lp as the pivot language. We name the translation model pivot model. The advantage of this method lies in that we can con- duct translation between Lf and Le even if there is no bilingual corpus available for this language pair. Moreover, if a small corpus is available for Lf-Le, we build another translation model, which is named standard model. Then, we build an interpo- lated model by performing linear interpolation on the standard model and the pivot model. Thus, the interpolated model can employ both the small Lf- Le corpus and the large Lf-Lp and Lp-Le corpora. We perform experiments on the Europarl corpus (Koehn, 2005). Using BLEU (Papineni et al., 2002) as a metric, our method achieves an absolute im- provement of 0.06 (22.13% relative) as compared with the standard model trained with 5,000 Lf-Le sentence pairs for French-Spanish translation. …

Content truncated to 500 words