Strategy planning processes often suffer from a lack of conceptual models that can be used to represent business strategies in a structured and standardized form. If natural langu...
Parallel corpora are a valuable resource for tasks such as cross-language information retrieval and data-driven natural language processing systems. Previously only small scale cor...
The end-to-end performance of natural language processing systems for compound tasks, such as question answering and textual entailment, is often hampered by use of a greedy 1-bes...
Jenny Rose Finkel, Christopher D. Manning, Andrew ...
Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For...
For a long time categorial grammars were regarded as "toys grammars". Indeed, in spite of a very solid theoretical base, categorial grammars remain rather marginal as so...