An MT System Embedding Pattern Knowledge
|Stella Markantonatou; Sokratis Sofianopoulos; V. Spilioti; George Tambouratzis; Marina Vassiliou; Olga Yannoutsou
|Van Eynde F.; Vandeghinste V.; Schuurman I.
|Proceedings of the 'New Approaches to Machine Translation' workshop held in conjunction with the 17th Meeting of Computational Linguistics in the Netherlands (CLIN 2007)
|Language and Speech group of the Radboud University Nijmegen
In this paper, we explain why we have adopted pattern matching for MT purposes and why we have embedded it into a hybrid approach. 'Patterns' here are understood as independent meaningful sub-sentential segments received in a systematic way. We describe the nature and size of the patterns used as well as the comparison algorithm developed. We discuss results obtained by matching patterns of different types and complexity in four different language pairs. Our experiments indicate that better results are obtained when matching the longest possible patterns.