Sign language machine translation overkill

Daniel Stein, Christoph Schmidt, Hermann Ney


Abstract
Sign languages represent an interesting niche for statistical machine translation that is typically hampered by the scarceness of suitable data, and most papers in this area apply only a few, well-known techniques and do not adapt them to small-sized corpora. In this paper, we will propose new methods for common approaches like scaling factor optimization and alignment merging strategies which helped improve our baseline. We also conduct experiments with different decoders and employ state-of-the-art techniques like soft syntactic labels as well as trigger-based and discriminative word lexica and system combination. All methods are evaluated on one of the largest sign language corpora available.
Anthology ID:
2010.iwslt-papers.17
Volume:
Proceedings of the 7th International Workshop on Spoken Language Translation: Papers
Month:
December 2-3
Year:
2010
Address:
Paris, France
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
337–344
Language:
URL:
https://aclanthology.org/2010.iwslt-papers.17
DOI:
Bibkey:
Cite (ACL):
Daniel Stein, Christoph Schmidt, and Hermann Ney. 2010. Sign language machine translation overkill. In Proceedings of the 7th International Workshop on Spoken Language Translation: Papers, pages 337–344, Paris, France.
Cite (Informal):
Sign language machine translation overkill (Stein et al., IWSLT 2010)
Copy Citation:
PDF:
https://aclanthology.org/2010.iwslt-papers.17.pdf