Витерби оқытуы

Statistically estimated phrase-based mod- els promised to further the state-of-the-art, however, several works reported a perfor- mance decrease with respect to heuristi- cally estimated phrase-based models. In this work we …...

We consider the search for a maximum likelihood assignment of hidden deriva- tions and grammar weights for a proba- bilistic context-free grammar, the problem approximately solved by “Viterbi train- ing.” …...