A method for generating a machine translation (MT) dictionary from parallel texts is described. This method utilizes both statistical information and linguistic information to obtain corresponding words or phrases in parallel texts. By combining these two types of information, translation pairs which cannot be obtained by a linguistic-based method can be extntcted. Over 70% accurate translation...

A method for generating a machine translation (MT) dictionary from parallel texts is described. This method utilizes both statistical information and linguistic information to obtain corresponding words or phrases in parallel texts. By combining these two types of information, translation pairs which cannot be obtained by a linguistic-based method can be extntcted. Over 70% accurate translation...

Post-Editing and machine translation are often studied from the viewpoint of efficiency (measured e.g. in words processed) or of quality (e.g. human judgement of fluency). Little is known, however, about how post-editing and machine translation change the linguistic profile of the texts produced in contrast to human translations. In this paper, we present a pilot study contrasting lexical profi...

as a culture-based phenomenon which involves both linguistic and social aspects, translation has been investigated from various perspectives. the present critical discourse analysis (cda)-based study is an attempt to probe into the manipulation of ideologies in translations of political texts. a cda approach, based on fairclough (1989), van dijk (2004) and farahzad (2007), was adopted to conduc...

Google Translate provides a multilingual machinetranslation service by automatically translating one written language to another. Google translate is allegedly limited in its accuracy in translation, however. This study investigated the accuracy of Google Chinese-to-English translation from the perspectives of formality and cohesion with two comparisons: Google translation with human expert tra...