':[his paper describes a rule-based machine learning approach to morphological processing in the system called XMAS. XMAS discovers and acquires linguistic rules from example...
We investigated the dictionary-based query translation method combining the translation disambiguation process using statistic cooccurrence information trained from the provided c...
Work on the production of texts in English describing instances of a particular event type from multiple news sources will be described. A system has been developed which extracts...
James R. Cowie, Yevgeny Ludovik, Hugo Molina-Salga...
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...