Enhancing Morphological Alignment for Translating Highly Inflected Languages

Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 743–751, Beijing, August 2010 Enhancing Morphological Alignment for Translating Highly Inflected Languages ∗ Minh-Thang Luong School of Computing National University of Singapore luongmin@comp.nus.edu.sg Min-Yen Kan School of Computing National University of Singapore kanmy@comp.nus.edu.sg Abstract We propose an unsupervised approach uti- lizing only raw corpora to enhance mor- phological alignment involving highly in- flected languages. Our method focuses on closed-class morphemes, modeling their influence on nearby words. Our language- independent model recovers important links missing in the IBM Model 4 align- ment and demonstrates improved end-to- end translations for English-Finnish and English-Hungarian. 1 Introduction Modern statistical machine translation (SMT) systems, regardless of whether they are word-, phrase- or syntax-based, typically use the word as the atomic unit of translation. While this approach works when translating between languages with limited morphology such as English and French, it has been found inadequate for morphologically- rich languages like Arabic, Czech and Finnish (Lee, 2004; Goldwater and McClosky, 2005; Yang and Kirchhoff, 2006). As a result, a line of SMT research has worked to incorporate mor- phological analysis to gain access to information encoded within individual words. In a typical MT process, word aligned data is fed as training data to create a translation model. In cases where a highly inflected language is involved, the current word-based alignment ap- proaches produce low-quality alignment, as the statistical correspondences between source and ∗This work was supported by a National Research Foun- dation grant “Interactive Media Search” (grant # R-252-000- 325-279) target words are diffused over many morpholog- ical forms. This problem has a direct impact on end translation quality. Our work addresses this shortcoming by proposing a morphologically sensitive approach to word alignment for language pairs involving a highly inflected language. In particular, our method focuses on a set of closed-class mor- phemes (CCMs), modeling their influence on nearby words. With the model, we correct er- roneous alignments in the initial IBM Model 4 runs and add new alignments, which results in im- proved translation quality. After reviewing related work, we give a case study for morpheme alignment in Section 3. Sec- tion 4 presents our four-step approach to construct and incorporate our CCM alignment model into the grow-diag process. Section 5 describes exper- iments, while Section 6 analyzes the system mer- its. We conclude with suggestions for future work. 2 Related Work MT alignment has been an active research area. One can categorize previous approaches into those that use language-specific syntactic information and those that do not. Syntactic parse trees have been used to enhance alignment (Zhang and Gildea, 2005; Cherry and Lin, 2007; DeNero and Klein, 2007; Zhang et al., 2008; Haghighi et al., 2009). With syntactic knowledge, modeling long distance reordering is possible as the search space is confined to plausible syntactic variants. However, they generally require language-specific tools and annotated data, making such approaches infeasible for many languages. Works that follow non-syntactic approaches, such as (Matusov et al., 743 i1 declare2 …

Content truncated to 500 words