Recent syntactic extensions of statistical translation models work with a synchronous context-free or tree-substitution grammar extracted from an automatically parsed parallel cor...
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...
This paper presents an attempt at building a large scale distributed composite language model that simultaneously accounts for local word lexical information, mid-range sentence s...
We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition...
Long distance word reordering is a major challenge in statistical machine translation research. Previous work has shown using source syntactic trees is an effective way to tackle ...