Abstract: Publication bias is the tendency for investigations with primarily nonstatistically significant findings to be withheld from the research record. Because publication bias...
Structured models often achieve excellent performance but can be slow at test time. We investigate structure compilation, where we replace structure with features, which are often...
Statistical parsers have become increasingly accurate, to the point where they are useful in many natural language applications. However, estimating parsing accuracy on a wide var...
In the framework of statistical machine translation (SMT), correspondences between the words in the source and the target language are learned from bilingual corpora on the basis ...
High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from ...