论文信息 - Statistical Machine Translation with Factored Translation Model: MWEs, Separation of Affixes, and Others

Statistical Machine Translation with Factored Translation Model: MWEs, Separation of Affixes, and Others

This paper discusses Statistical Machine Translation when the target side is morphologically richer language. This paper intends to discuss what is not covered by the factored translation model of Moses especially targetting EN--JP translation: the effect of Multi-Word Expressions, affixes separation, and other monolingual morphological issues. We intend to discuss these over a factored translation model.

Andy Way | Alexandru Ceausu | Tsuyoshi Okita

[1] Andy Way,et al. Gap Between Theory and Practice: Noise Sensitive Word Alignment in Machine Translation , 2010, WAPA.

[2] Masao Utiyama,et al. Overview of the Patent Translation Task at the NTCIR-7 Workshop , 2008, NTCIR.

[3] Miles Osborne,et al. Statistical Machine Translation , 2010, Encyclopedia of Machine Learning and Data Mining.

[4] Philipp Koehn,et al. Factored Translation Models , 2007, EMNLP.

[5] Josef van Genabith,et al. Factor templates for factored machine translation models , 2010, IWSLT.

[6] Philipp Koehn,et al. Enriching Morphologically Poor Languages for Statistical Machine Translation , 2008, ACL.

[7] Andy Way,et al. Multi-Word Expression-Sensitive Word Alignment , 2010 .

[8] Alexandru Ceauşu. Maximum Entropy Tiered Tagging , 2006 .