2011.iwslt-evaluation.20@ACL

#1 SCFG latent annotation for machine translation [PDF] [Copy] [Kimi¹] [REL]

Authors: Tagyoung Chung, Licheng Fang, Daniel Gildea

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.

Subject: IWSLT.2011 - Evaluation Campaign

---