Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
Electronic written texts used in computermediated interactions (e-mails, blogs, chats, etc) present major deviations from the norm of the language. This paper presents an comparat...
The need for syntactically annotated data for use in natural language processing has increased dramatically in recent years. This is true especially for parallel treebanks, of whi...
We present a method for learning to find English to Chinese transliterations on the Web. In our approach, proper nouns are expanded into new queries aimed at maximizing the probab...
We consider multi-pushdown automata, a multi-stack extension of pushdown automata that comes with a constraint on stack operations: a pop can only be performed on the first non-emp...
Mohamed Faouzi Atig, Benedikt Bollig, Peter Haberm...