شماره ركورد كنفرانس :
3540
عنوان مقاله :
Improving Reordering models with Phrase number feature for statistical Machine Translation
Author/Authors :
Neda Noormohammadi Heuman Language Technology Lab - Amirkabir University Of Technology , Zahra Rahimi Heuman Language Technology Lab - Amirkabir University Of Technology , Shahram Khadivi Heuman Language Technology Lab - Amirkabir University Of Technology
كليدواژه :
reorder-ing graph , distance based reordering model , Phrase number feature , lexicalized reor-dering model , Reordering model , Statistical machine translation
عنوان كنفرانس :
همايش بين المللي هوش مصنوعي و پردازش سيگنال
چكيده لاتين :
Reordering models in statistical machine translation are crucial for many language pairs. Specifically those with very different sentence structure like Persian and English. In this paper, we enhance the well-known lexical model by taking into account the position of the phrase in the target language. We observe over 1.7 percent relative improvement in BLEU score when com-paring the baseline lexical reordering model with the proposed model in an English-Persian task.
