Margin Infused Relaxed Algorithm for Moses
Eva Hasler, Barry Haddow, Philipp Koehn
Source record
Source: Crossref
Published: Oct 1, 2011
DOI: 10.2478/v10108-011-0012-3
Open original source ↗Source abstract
Margin Infused Relaxed Algorithm for Moses 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.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.