Publication - Using Patterns for Machine Translation (MT)

Using Patterns for Machine Translation (MT)

Research Area:  
In Proceedings


Year: 2006
Authors: Stella Markantonatou; Sokratis Sofianopoulos; V. Spilioti; George Tambouratzis; Marina Vassiliou; Olga Yannoutsou
Editor: George Potamias;Lonning J.T.; Oepen S.
Book title: Proceedings of EAMT 11th Annual Conference
Pages: 239-246
Address: Oslo, Norway
Organization: European Association for Machine Translation (ΕΑΜΤ)
Date: June 19-20
ISBN: 82-7368-294-3
In this paper an innovative approach is presented for MT, which is based on pattern matching techniques, relies on extensive target language monolingual corpora and employs a series of similarity weights between the source and the target language. Our system is based on the notion of ‘patterns’, which are viewed as ‘models ’ of target language strings, whose final form is defined by the corpus.