Discriminative Reordering Models for Statistical Machine Translation

In large size high resolution plasma panels, a smaller discharge gap between the electrodes reduces the operating margin of the panel, i.e., the difference between the maximum and minimum sustain voltage (Vsmax and Vsmin). Rather than preset these values which vary with each panel at the time of fabrication, the invention provides a control system for determining the Vsmax and Vsmin and the optimum operating point between these values for each panel. An associated microprocessor determines the Vsmin for each panel through a testing algorithm, and the Vsmax is provided by either adding a predetermined increment to the Vsmin or by a testing sequence. The operating point is designated as a predetermined increment below Vsmax. The invention operates each time the panel is turned on, thereby compensating for voltage drift or other panel parameter variations. By using a high speed microprocessor, the entire sequence is accomplished in a short time, while exercising the cells through the test sequence eliminates some of the "start-up" problems sometimes associated with such displays.

[1]  Franz Josef Och,et al.  An Efficient Method for Determining Bilingual Word Classes , 1999, EACL.

[2]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[3]  Mark Przybocki,et al.  NIST 2005 machine translation evaluation official results , 2005 .

[4]  Hermann Ney,et al.  The RWTH Phrase-based Statistical Machine Translation System , 2005, IWSLT.

[5]  Stanley F. Chen,et al.  A Gaussian Prior for Smoothing Maximum Entropy Models , 1999 .

[6]  Hermann Ney,et al.  Improvements in Phrase-Based Statistical Machine Translation , 2004, NAACL.

[7]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[8]  Hermann Ney,et al.  Discriminative Training and Maximum Entropy Models for Statistical Machine Translation , 2002, ACL.

[9]  William H. Press,et al.  Numerical recipes in C , 2002 .

[10]  Philipp Koehn,et al.  Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models , 2004, AMTA.

[11]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[12]  Dekai Wu,et al.  Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora , 1997, CL.

[13]  Shankar Kumar,et al.  Local Phrase Reordering Models for Statistical Machine Translation , 2005, HLT.

[14]  Chiori Hori,et al.  Overview of the IWSLT 2005 Evaluation Campaign , 2005, IWSLT.

[15]  Hermann Ney,et al.  Improved Alignment Models for Statistical Machine Translation , 1999, EMNLP.

[16]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[17]  Tong Zhang,et al.  A Localized Prediction Model for Statistical Machine Translation , 2005, ACL.

[18]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

[19]  John Cocke,et al.  A Statistical Approach to Machine Translation , 1990, CL.

[20]  Taro Watanabe,et al.  Reordering Constraints for Phrase-Based Statistical Machine Translation , 2004, COLING.

[21]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[22]  Philipp Koehn,et al.  Explorer Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation , 2005 .

[23]  J. Darroch,et al.  Generalized Iterative Scaling for Log-Linear Models , 1972 .

[24]  Eiichiro Sumita,et al.  Toward a Broad-coverage Bilingual Corpus for Speech Translation of Travel Conversations in the Real World , 2002, LREC.