2009 · 38 citations · 8 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingLanguage ModelsPattern RecognitionRepresentation LearningSequence AlignmentInput SegmentationMany-to-many MatchingOnline PredictionPrediction OnlineSegmentationSequence ModelingSequence PredictionSequence Representation Learning
We present DirecTL: an online discriminative sequence prediction model that employs a many-to-many alignment between target and source. Our system incorporates input segmentation, target character prediction, and sequence modeling in a unified dynamic programming framework. Experimental results suggest that DirecTL is able to independently discover many of the language-specific regularities in the training data.
8
Making Large-Scale SVM Learning Practical
Thorsten Joachims · Technical reports · 2006 · 4.3K citations · Full text
A joint source-channel model for machine transliteration
Haizhou Li, Min Zhang, Jian Su · 2004 · 253 citations · Full text
A new algorithm for the alignment of phonetic sequences
Grzegorz Kondrak · 2000 · 167 citations