We formulate the problem of nonprojective dependency parsing as a polynomial-sized integer linear program. Our formulation is able to handle non-local output features in an effici...
Abstract. As software systems become bigger and more complex, software developers need to cope with a growing amount of information and knowledge. The knowledge generated during th...
We present a novel approach to integrate transliteration into Hindi-to-Urdu statistical machine translation. We propose two probabilistic models, based on conditional and joint pr...
Nadir Durrani, Hassan Sajjad, Alexander Fraser, He...
Syntactic machine translation systems extract rules from bilingual, word-aligned, syntactically parsed text, but current systems for parsing and word alignment are at best cascade...
Partial information can trigger a complete memory. At the same time, human memory is not perfect. A cue can contain enough information to specify an item in memory, but fail to tr...
David Jacobs, Bas Rokers, Archisman Rudra, Zili Li...