期刊名称：The Prague Bulletin of Mathematical Linguistics
印刷版ISSN：0032-6585
电子版ISSN：1804-0462
出版年度：2011
卷号：96
期号：1
页码：69-78
DOI：10.2478/v10108-011-0012-3
语种：English
出版社：Walter de Gruyter GmbH
摘要：We describe an open-source implementation of the Margin Infused Relaxed Algorithm (MIRA) for statistical machine translation (SMT). The implementation is part of the Moses toolkit and can be used as an alternative to standard minimum error rate training (MERT). A description of the implementation and its usage on core feature sets as well as large, sparse feature sets is given and we report experimental results comparing the performance of MIRA with MERT in terms of translation quality and stability.
Loading...
