Hybrid Algorithm for Word-Level Alignment of Parallel Texts
- Cite this paper as:
- Cendejas E., Barceló G., Gelbukh A., Sidorov G. (2010) Hybrid Algorithm for Word-Level Alignment of Parallel Texts. In: Horacek H., Métais E., Muñoz R., Wolska M. (eds) Natural Language Processing and Information Systems. NLDB 2009. Lecture Notes in Computer Science, vol 5723. Springer, Berlin, Heidelberg
Given a text in two languages, word alignment task consists of identifying in the two variants of the text specific word occurrences that are mutual translations. The majority of existing text alignment systems follow either a linguistic or a statistical approach. We argue for that both approaches are insufficient when used separately, and suggest a flexible algorithm that combines statistical and linguistic techniques.