Multi-Alignment Templates Induction

Article type: Research Article

Authors: Laukaitis, Algirdas | Vasilecas, Olegas

Affiliations: Faculty of Fundamental Sciences, Vilnius Gediminas Technical University, Saulėtekio al. 11, LT-10223 Vilnius, Lithuania, e-mail: algirdas.laukaitis@fm.vgtu.lt, olegas.vasilecas@fm.vgtu.lt

Abstract: This paper examins approaches for translation between English and morphology-rich languages. Experiment with English–Russian and English–Lithuanian revels that “pure” statistical approaches on 10 million word corpus gives unsatisfactory translation. Then, several Web-available linguistic resources are suggested for translation. Syntax parsers, bilingual and semantic dictionaries, bilingual parallel corpus and monolingualWeb-based corpus are integrated in one comprehensive statistical model. Multi-abstraction language representation is used for statistical induction of syntactic and semantic transformation rules called multi-alignment templates. The decodingmodel is described using the feature functions, a log-linear modeling approach and A* search algorithm. An evaluation of this approach is performed on the English–Lithuanian language pair. Presented experimental results demonstrates that the multi-abstraction approach and hybridization of learning methods can improve quality of translation.

Keywords: machine translation, natural language processing, statistical induction, EM algorithm, A* search

Journal: Informatica, vol. 19, no. 4, pp. 535-554, 2008