International Workshop on Spoken Language Translation (IWSLT) 2011
San Francisco, CA, USA
We discuss learning latent annotations for synchronous context-free grammars (SCFG) for the purpose of improving machine translation. We show that learning annotations for nonterminals results in not only more accurate translation, but also faster SCFG decoding.
Bibliographic reference. Chung, Tagyoung / Fang, Licheng / Gildea, Daniel (2011): "SCFG latent annotation for machine translation", In IWSLT-2011, 151-158.