Maximum likelihood and discriminative training of direct translation models

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 1998, Pages 189-192

  Papineni, K A ^a   Roukos, S ^a   Ward, R T ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CONDITIONAL PROBABILITIES; CONDITIONAL PROBABILITY DISTRIBUTIONS; DISCRIMINATIVE TRAINING; NATURAL LANGUAGES; TARGET LANGUAGE; THREE COMPONENT; TRAINING CORPUS; TRANSLATION MODELS;

FORMAL LANGUAGES; PROBABILITY DISTRIBUTIONS;

SIGNAL PROCESSING;

EID: 0031632922     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.674399     Document Type: Conference Paper

References (6)

1. P. F. Brown et al. "The mathematics of statistical machine translation: Parameter estimation", Computational Lingustics, 19 (2), 263-311, June 1993.
2. W. Chou et al, "Segmental GPD training of HMM based speech recognizer," Proceedings of the IEEE ICASSP-92, I, 473-476
3. L. Hirschman, "Multi-Site Data Collection for a Spoken Language Corpus", Proceedings of the DARPA Speech and Natural Language Workshop, pp 7-14, Harriman, NY, Feb 1992.
4. S. Delia Pietra et al, "Inducing features of random fields," CMU Technical Report CMU-CS-95-144, 1995.
5. K. Papineni et al, "Feature-based language understanding," Proceedings of EU-ROSPEECH'97, 3, 1435-1438.
6. K. Papineni, "Efficient discriminative training of exponential probability models," Manuscript preparation.