2004 · 51 citations · 15 references
ComputingComputer ScienceTranslation StudiesCorpus-based Translation StudiesNatural Language ProcessingTranslation TheoryLanguage ModelingMachine TranslationSpeech RecognitionTranslation Quality AssessmentEvaluation MetricsLog-linear RegressionLog-logistic ModelSpeech TranslationSpeech-to-text TranslationStatistical Machine TranslationTranslation Quality MetricsWord Error Rate
Based upon a statistically trained speech translation system, in this study, we try to combine distinctive features derived from the two modules: speech recognition and statistical machine translation, in a loglinear model. The translation hypotheses are then rescored and translation performance is improved. The standard translation evaluation metrics, including BLEU, NIST, multiple reference word error rate and its position independent counterpart, were optimized to solve the weights of the features in the log-linear model. The experimental results have shown significant improvement over the baseline IBM model 4 in all automatic translation evaluation metrics. The largest was for BLEU, by 7.9% absolute.
15
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
William H. Press, Saul A. Teukolsky, William T. Vetterling et al. · 1994 · 15.4K citations
A Systematic Comparison of Various Statistical Alignment Models
Franz Josef Och, Hermann Ney · Computational Linguistics · 2003 · 3.9K citations · Full text