Title MT Goes Farming: Comparing Two Machine Translation Approaches on a New Domain
Author(s) Per Weijnitz, Eva Forsbom, Ebba Gustavii, Eva Pettersson, Jörg Tiedemann

Department of Linguistics and Philology, Uppsala University, Box 635, S-751 26 Uppsala, Sweden, {perweij,evafo,ebbag,evapet,joerg}@stp.ling.uu.se

Session P25-EW
Abstract In the paper we present detailed analyses of two machine translation systems when applied to documents of a previously unseen domain: agricultural texts from the European Union. The two systems compared are a statistical machine translation (SMT) system using the freely available ISI ReWrite Decoder, and the rule-based machine translation system MATS. For the purpose of comparison we use a sentence-aligned Swedish-English corpus of approximately 75,000 words per language, where 90\% are used for training and 10% are used for evaluation. In the paper we discuss the outcome of automatic evaluation and the results of our manual quality assessment.
Keyword(s) Machine translation, transfer-based MT, statistical machine translation, SMT, MT evaluation
Language(s) Swedish, English
Full Paper 735.pdf