MT Goes Farming: Comparing Two Machine Translation Approaches on a New Domain
نویسندگان
چکیده
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 (Germann, 2003a), and the rule-based machine translation system MATS (Sågvall Hein et al., 2002). 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.
منابع مشابه
MT goes farming
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 (Germann, 2003a), and the rule-based machine translation system MATS (Sågvall Hein et al., 2002)...
متن کاملبهبود و توسعه یک سیستم مترجمیار انگلیسی به فارسی
In recent years, significant improvements have been achieved in statistical machine translation (SMT), but still even the best machine translation technology is far from replacing or even competing with human translators. Another way to increase the productivity of the translation process is computer-assisted translation (CAT) system. In a CAT system, the human translator begins to type the tra...
متن کاملLinguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation
In this paper, we study AMR-to-text generation, framing it as a translation task and comparing two different MT approaches (Phrasebased and Neural MT). We systematically study the effects of 3 AMR preprocessing steps (Delexicalisation, Compression, and Linearisation) applied before the MT phase. Our results show that preprocessing indeed helps, although the benefits differ for the two MT models...
متن کاملA Revised and Extended Version of Latent Domain Translation Models in Mix-of-Domains Haystack
The problem of selecting data for training machine translation (MT) systems has received attention in the past years because training MT systems on larger corpora does not always yield improved performance. The data selection problem aims at selecting training data from a mixeddomain corpus for a translation task exemplified by a small sample of in-domain data. In (Cuong and Sima’an, 2014b) we ...
متن کاملComparing Corpus-based MT Approaches Using Restricted Resources
Machine translation (MT) plays an important role in multilingual communication. Dealing with natural language and a diversity of language-pairs, it is not always possible to have sufficient (linguistic) resources for a specific MT approach and a diversity of domains. In this paper we compare a statistical MT system with an example-based one and a hybrid system. For a better overview we include ...
متن کامل