Paper: English to Hungarian Morpheme-based Statistical Machine Translation System with Reordering Rules

ACL ID W13-2808
Title English to Hungarian Morpheme-based Statistical Machine Translation System with Reordering Rules
Venue Workshop on Hybrid Approaches to Translation
Session
Year 2013
Authors

Phrase-based statistical machine transla- tion systems can generate translations of reasonable quality in the case of language pairs with similar structure and word or- der. However, if the languages are more distant from a grammatical point of view, the quality of translations is much behind the expectations, since the baseline trans- lation system cannot cope with long dis- tance reordering of words and the mapping of word internal grammatical structures. In our paper, we present a method that tries to overcome these problems in the case of English-Hungarian translation by apply- ing reordering rules prior to the translation process and by creating morpheme-based and factored models. Although automatic evaluation scores do not reliably reflect the improvement in all cases, human evalua- ...