A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages

Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 148–157, MIT, Massachusetts, USA, 9-11 October 2010. c⃝2010 Association for Computational Linguistics A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages∗ Minh-Thang Luong Preslav Nakov Department of Computer ScienceMin-Yen Kan National University of Singapore 13 Computing Drive Singapore 117417 {luongmin,nakov,kanmy}@comp.nus.edu.sg Abstract We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. Our model extends the classic phrase-based model by means of (1) word boundary-aware morpheme-level phrase extraction, (2) minimum error-rate training for a morpheme-level translation model using word-level BLEU, and (3) joint scoring with morpheme- and word-level lan- guage models. Further improvements are achieved by combining our model with the classic one. The evaluation on English to Finnish using Europarl (714K sentence pairs; 15.5M English words) shows statistically sig- nificant improvements over the classic model based on BLEU and human judgments. 1 Introduction The fast progress of statistical machine translation (SMT) has boosted translation quality significantly. While research keeps diversifying, the word remains the atomic token-unit of translation. This is fine for languages with limited morphology like English and French, or no morphology at all like Chinese, but it is inadequate for morphologically rich languages like Arabic, Czech or Finnish (Lee, 2004; Goldwater and McClosky, 2005; Yang and Kirchhoff, 2006). ∗This research was sponsored in part by CSIDM (grant # 200805) and by a National Research Foundation grant entitled “Interactive Media Search” (grant # R-252-000-325-279). There has been a line of recent SMT research that incorporates morphological analysis as part of the translation process, thus providing access to the information within the individual words. Unfortu- nately, most of this work either relies on language- specific tools, or only works for very small datasets. Below we propose a language-independent ap- proach to SMT of morphologically rich lan- guages using a hybrid morpheme-word representa- tion where the basic unit of translation is the mor- pheme, but word boundaries are respected at all stages of the translation process. We use unsuper- vised morphological analysis and we incorporate its output into the process of translation, as opposed to relying on pre-processing and post-processing only as has been done in previous work. The remainder of the paper is organized as fol- lows. Section 2 reviews related work. Sections 3 and 4 present our morphological and phrase merging enhancements. Section 5 describes our experiments, and Section 6 analyzes the results. Finally, Section 7 concludes and suggests directions for future work. 2 Related Work Most previous work on morphology-aware ap- proaches relies heavily on language-specific tools, e.g., the TreeTagger (Schmid, 1994) or the Buck- walter Arabic Morphological Analyzer (Buckwal- ter, 2004), which hampers their portability to other languages. Moreover, the prevalent method for incorporating morphological information is by heuristically-driven pre- or post-processing. For example, Sadat and Habash (2006) use different combinations of …

Content truncated to 500 words