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.
Cite as: Chung, T., Fang, L., Gildea, D. (2011) SCFG latent annotation for machine translation. Proc. International Workshop on Spoken Language Translation (IWSLT 2011), 151-158
@inproceedings{chung11_iwslt,
author={Tagyoung Chung and Licheng Fang and Daniel Gildea},
title={{SCFG latent annotation for machine translation}},
year=2011,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2011)},
pages={151--158}
}