Word-dependent transition models in HMM based word alignment...

Details Word-dependent transition models in HMM based word alignment... Word-dependent transition models in HMM based word alignment...

2007-10-30

2011-11-15

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Linguistics

Natural language

C704S010000, C704S002000

Reexamination Certificate

active

08060360

ABSTRACT:
A word alignment modeler uses probabilistic learning techniques to train “word-dependent transition models” for use in constructing phrase level Hidden Markov Model (HMM) based word alignment models. As defined herein, “word-dependent transition models” provide a probabilistic model wherein for each source word in training data, a self-transition probability is modeled in combination with a probability of jumping from that particular word to a different word, thereby providing a full transition model for each word in a source phrase. HMM based word alignment models are then used for various word alignment and machine translation tasks. In additional embodiments sparse data problems (i.e., rarely used words) are addressed by using probabilistic learning techniques to estimate word-dependent transition model parameters by maximum a posteriori (MAP) training.

REFERENCES:
patent: 4827521 (1989-05-01), Bahl et al.
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5812975 (1998-09-01), Komori et al.
patent: 6161083 (2000-12-01), Franz et al.
patent: 6182026 (2001-01-01), Tillmann et al.
patent: 6292769 (2001-09-01), Flanagan et al.
patent: 6304841 (2001-10-01), Berger et al.
patent: 6697779 (2004-02-01), Bellegarda et al.
patent: 7209875 (2007-04-01), Quirk et al.
patent: 7219051 (2007-05-01), Moore
patent: 7239998 (2007-07-01), Xun
patent: 7340388 (2008-03-01), Soricut et al.
patent: 2004/0030551 (2004-02-01), Marcu et al.
patent: 2005/0216253 (2005-09-01), Brockett
patent: 2006/0190241 (2006-08-01), Goutte et al.
patent: 2007/0083357 (2007-04-01), Moore et al.
patent: 2008/0243481 (2008-10-01), Brants et al.
patent: 2008/0300857 (2008-12-01), Barbaiani et al.
“Yahoo! Babel Fish—Text Translation and Web Page Translation” retrieved from <http://web.archive.org/web/20061005204237/http://babelfish.yahoo.com/> on Sep. 21, 2010, indexed Oct. 5, 2006.
Varea et al. “Improving alignment quality in statistical machine translation using context-dependent maximum entropy models” 2002.
Kumar et al. “Local Phrase Reordering Models for Statistical Machine Translation” 2005.
Carpuat et al. “Improving Statistical Machine Translation using Word Sense Disambiguation” Jul. 2007.
Siohan et al. “Joint Maximum a Posteriori Estimation of Transformation and Hidden Markov Model Parameters” 2000.
Blunsom et al. “Discriminative Word Alignment with Conditional Random Fields” Jul. 2006.
Barbaiani et al. “Asymmetric Term Alignment with Selective Contiguity Constraints by Multi-Tape Automata” Sep. 24, 2007.
DeNero et al. “TailoringWord Alignments to Syntactic Machine Translation” Jun. 23-30, 2007.
Al-Onaizan et al. “Distortion Models for Statistical Machine Translation” Jul. 2006.
Cherry et al. “A Probability Model to Improve Word Alignment” Jul. 2003.
Deng et al. “HMM Word and Phrase Alignment for Statistical Machine Translation” 2005.
Zhao et al. “Inner-Outer Bracket Models for Word Alignment using Hidden Blocks” 2005.
Deng, et al., “HMM Word and Phrase Alignment for Statistical Machine Translation”, Human Language Technology Conference, Date: 2005, pp. 169-176, Association for Computational Linguistics, Morristown, NJ, USA.
Brown, et al., “The Mathematics of Statistical Machine Translation: Parameter Estimation”, Date: 1993, vol. 19, No. 2, pp. 263-311, Computational Linguistics.
Deng, et al., “HMM Word and Phrase Alignment for Statistical Machine Translation”, Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language, Date: Oct. 2005, pp. 169-176, Trumpington Street, Cambridge, UK.
Franz Josef Och, “Minimum Error Rate Training in Statistical Machine Translation”, Date: Jul. 2003, pp. 160-167, University of Southern California, CA.
Gauvain, et al., “Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains”, Date: Apr. 1994, vol. 2, No. 2.
Koehn, et al., “Statistical Phrase-Based Translation”, Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology—vol. 1, Date: 2003, pp. 48-54.
L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition”. Date: Feb. 1989, vol. 77, Issue: 2, p. 257-286.
Liang, et al., “Alignment by Agreement”, Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL, Date: Jun. 2006, pp. 104-111, Berkeley, CA.
Moore, et al., “Improved Discriminative Bilingual Word Alignment”, Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL, Date: 2006, pp. 513-520.
Och, et al., “A Comparison of Alignment Models for Statistical Machine Translation”, Proceedings of the 18th conference on Computational linguistics—vol. 2, Date: 2000, pp. 1086-1090, Association for Computational Linguistics, USA.
Och, et al., “Discriminative Training and Maximum Entropy Models for Statistical Machine Translation”, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Date: 2001, pp. 295-302, Association for Computational Linguistics, USA.
Och, et al., “Improved Statistical Alignment Models”, Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, Date: 2000, pp. 440-447.
Papineni, et al., “Bleu: A Method for Automatic Evaluation of Machine Translation”, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Date: 2001, pp. 311-318, Association for Computational Linguistics, USA.
Toutanova, et al., Extensions to HMM-based Statistical Word Alignment Models, Proceedings of the ACL-02 conference on Empirical methods in natural language processing—vol. 10, Date: 2002, pp. 87-94, Association for Computational Linguistics, USA.
Vogel, et al., “HMM-Based Word Alignment in Statistical Translation”, Proceedings of the 16th conference on Computational linguistics—vol. 2, Date: 1996, pp. 836-841, Association for Computational Linguistics, USA.
Zhang, et al., “Stochastic Lexicalized Inversion Transduction Grammar for Alignment”, Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, Date: 2005, pp. 475-482, Association for Computational Linguistics, USA.
Koehn., “Pharaoh: A Beam Search Decoder for Phrase Based Statistical Machine Translation Models. In Proceedings of AMTA”.2004b.
F. J. Och and H. Ney. 2000c. “Giza++: Training of statistical translation models.”, http://www.fjoch.com/GIZA++.html.

Affiliated with

Also associated with

Rating

Word-dependent transition models in HMM based word alignment... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Word-dependent transition models in HMM based word alignment..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Word-dependent transition models in HMM based word alignment... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4295194