DocumentCode :
2788771
Title :
Machine translation: boundaries and practice in the late ´90s
Author :
Lewis, Terence
fYear :
1997
fDate :
35472
Firstpage :
42552
Lastpage :
42556
Abstract :
Machine translation, which is less commonly referred to as computer translation or automatic translation, is the generally accepted name for any system which uses a computer "to transform a text in one language into some kind of text in another natural language". Fully automatic translation lies at one end of the scale and the work of the human translator armed with pencil and paper at the other. Between them are a number of possibilities for collaboration between man and computer which include word processing, terminology databases, voice recognition and translation memory systems. Machine translation (MT) and translation memory (TM) systems are frequently confused. Machine translation essentially involves the generation of target text from possibly unseen source text; translation memory programs are designed to retrieve from pairs of matching strings stored in a database-a sophisticated electronic phrasebook, stocked with the translator\´s own work. MT developers have been looking at ways of incorporating full-sentence retrieval into their programs, whilst some TM vendors have introduced third-party translation engines to handle unseen text. The future translation environment will probably exhibit both aspects by design rather than as add-ons
fLanguage :
English
Publisher :
iet
Conference_Titel :
Language Toolkit for Engineers in Business (Digest No. 1997/058), IEE Colloquium on the
Conference_Location :
London
Type :
conf
DOI :
10.1049/ic:19970328
Filename :
598659
Link To Document :
بازگشت