The Universal Networking Language in Action in English-Arabic Machine Translation
暂无分享,去创建一个
This paper presents an interlingua approach to the machine translation of lengthy documents. This appr oach is based on encoding the source text in the form of universa l semantic networks, using the Universal Networking Language, UNL interlingua, which can then be decoded back int o any natural language. This UNL technology has bee n applied to 1000 pages from the Encyclopedia of Life support Systems (EOLSS) in order to be translated into the six official languages of the UNESCO. This paper summarizes the overall strategy adopted with a focus on the decod ing of UNL documents into Arabic.
[1] Noha Adly,et al. A Semantic-Based Approach for Multilingual Translation of Massive Documents , 2007 .
[2] Antonio Moreno,et al. Syntax to Semantics Transformation: Application to Treebanking , 2004, FCP@NAACL-HLT.
[3] Alon Lavie,et al. The significance of recall in automatic metrics for MT evaluation , 2004, AMTA.
[4] Salim Roukos,et al. Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.