Soft string-to-dependency hierarchical machine translation

Jan-Thorsten Peter, Matthias Huck, Hermann Ney, Daniel Stein


Abstract
In this paper, we dissect the influence of several target-side dependency-based extensions to hierarchical machine translation, including a dependency language model (LM). We pursue a non-restrictive approach that does not prohibit the production of hypotheses with malformed dependency structures. Since many questions remained open from previous and related work, we offer in-depth analysis of the influence of the language model order, the impact of dependency-based restrictions on the search space, and the information to be gained from dependency tree building during decoding. The application of a non-restrictive approach together with an integrated dependency LM scoring is a novel contribution which yields significant improvements for two large-scale translation tasks for the language pairs Chinese–English and German–French.
Anthology ID:
2011.iwslt-papers.8
Volume:
Proceedings of the 8th International Workshop on Spoken Language Translation: Papers
Month:
December 8-9
Year:
2011
Address:
San Francisco, California
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
246–253
Language:
URL:
https://aclanthology.org/2011.iwslt-papers.8
DOI:
Bibkey:
Cite (ACL):
Jan-Thorsten Peter, Matthias Huck, Hermann Ney, and Daniel Stein. 2011. Soft string-to-dependency hierarchical machine translation. In Proceedings of the 8th International Workshop on Spoken Language Translation: Papers, pages 246–253, San Francisco, California.
Cite (Informal):
Soft string-to-dependency hierarchical machine translation (Peter et al., IWSLT 2011)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2011.iwslt-papers.8.pdf