Generating a phrase translation model by iteratively...

Data processing: speech signal processing – linguistics – language – Linguistics – Translation machine

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S277000, C704S005000

Reexamination Certificate

active

07983898

ABSTRACT:
A phrase translation model is trained without assuming a segmentation of training data into non-overlapping phrase pairs. Instead, the training algorithm assumes that any particular phrase instance has only a single phrase instance in another language as its translation in that instance, but that phrases can overlap. The model is trained by computing expected phrase alignment counts, deriving selection probabilities from current estimates of translation probabilities and then re-estimating phrase translation probabilities according to the expected phrase alignment counts computed. The model is trained by iterating over these steps until one or more desired stopping criteria are reached. The trained model can be deployed in a machine translation system.

REFERENCES:
patent: 5805832 (1998-09-01), Brown
patent: 6304841 (2001-10-01), Berger
patent: 6885985 (2005-04-01), Hull
patent: 6990439 (2006-01-01), Xun
patent: 7054803 (2006-05-01), Eisele
patent: 7200550 (2007-04-01), Menezes
patent: 7206736 (2007-04-01), Moore
patent: 2004/0030551 (2004-02-01), Marcu
patent: 2005/0038643 (2005-02-01), Koehn
patent: 2006/0015318 (2006-01-01), Moore
patent: 2006/0015320 (2006-01-01), Och
patent: 2007/0016397 (2007-01-01), Lu
David Chiang, “A Hierarchical Phrase-Based Model for Statistical Machine Translation” Proceedings of the 43rdAnnual Meeting of the ACL, pp. 263-270 Ann Arbor, Jun. 2005.
PCT International Search Report Application No. PCT/US2008/063403.
Luke S. Zettlermoyer et al., “Selective Phrase Pair Extraction for Improved Statistical Machine Translation” Proceedings of NAACL HTL 2007, Apr. 26, 2007. See Abstract, section 1-2.
Ashish Venugopal et al. “Effective Phrase Translation Extraction from Alignment Models” Proceedings of the 41stAnnual Meeting of the Association for Computational Linguistics, Jul. 7, 2005. See abstract, section 2-4.
Robert C. Moore et al., “An Iteratively-Trained Segmentation-Free Translation Model for Statistical Machine Translation” In Proceedings of the Second Workshop on Statistical Machine Translation, Jun. 23, 2007. See Abstract, section 2-5.
Stephan Vogel, et al. “The CMU Statistical Machine Translation System”, Language Technologies Institute, Carnegie Mellon University, 8 pages, 2003.
Richard Zens, et al., “Phrase-Based Statistical Machine Translation” Human Language Technology and Pattern Recognition, Germany 15 pages, 2002.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Generating a phrase translation model by iteratively... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Generating a phrase translation model by iteratively..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Generating a phrase translation model by iteratively... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2731973

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.