We argue that some of the computational complexity associated with estimation of stochastic attributevalue grammars can be reduced by training upon an informative subset of the fu...
The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained ...
We examine effects that empty categories have on machine translation. Empty categories are elements in parse trees that lack corresponding overt surface forms (words) such as drop...
We propose a relaxed correspondence assumption for cross-lingual projection of constituent syntax, which allows a supposed constituent of the target sentence to correspond to an u...
This paper proposes a data-driven method for concept-to-text generation, the task of automatically producing textual output from non-linguistic input. A key insight in our approac...