Abstract
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.
| Original language | English |
|---|---|
| Pages (from-to) | 69-78 |
| Number of pages | 10 |
| Journal | Prague Bulletin of Mathematical Linguistics |
| Volume | 96 |
| DOIs | |
| Publication status | Published - 2011 |