SCFG latent annotation for machine translation

Tagyoung Chung, Licheng Fang, Daniel Gildea


Abstract
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.
Anthology ID:
2011.iwslt-evaluation.20
Volume:
Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 8-9
Year:
2011
Address:
San Francisco, California
Venue:
IWSLT
SIG:
Publisher:
Note:
Pages:
151–158
Language:
URL:
https://aclanthology.org/2011.iwslt-evaluation.20
DOI:
Bibkey:
Cite (ACL):
Tagyoung Chung, Licheng Fang, and Daniel Gildea. 2011. SCFG latent annotation for machine translation. In Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 151–158, San Francisco, California.
Cite (Informal):
SCFG latent annotation for machine translation (Chung et al., IWSLT 2011)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2011.iwslt-evaluation.20.pdf