DFKI-LT - Linguistically-Enriched Models for Bulgarian-to-English Machine Translation
Linguistically-Enriched Models for Bulgarian-to-English Machine Translation
1 Proceedings of the Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation,
In this paper, we present our linguistically-enriched Bulgarian-to-English statistical machine translation model, which takes a statistical machine translation (SMT) system as backbone various linguistic features as factors. The motivation is to take advantages of both the robustness of the SMT system and the rich linguistic knowledge from morphological analysis as well as the hand-crafted grammar resources. The automatic evaluation has shown promising results and our extensive manual analysis confirms the high quality of the translation the system delivers. The whole framework is also extensible for incorporating information provided by different sources.
Files: BibTeX, W12-4202, W12-4202.pdf