This paper presents a novel way of improving POS tagging on heterogeneous data. First, two separate models are trained (generalized and domain-specific) from the same data set by...
Statistical MT has made great progress in the last few years, but current translation models are weak on re-ordering and target language fluency. Syntactic approaches seek to reme...
Michel Galley, Jonathan Graehl, Kevin Knight, Dani...
The main idea of iceberg data cubing methods relies on optimization techniques for computing only the cuboids cells above certain minimum support threshold. Even using such approac...
Collinear arrangement of objects (such as, text elements or continuous lines) is integral part of any office document image, whether structured or unstructured. The ability to ana...