Esmé Manandise

  • Citations Per Year
Learn More
Machine Translation (MT) systems that process unrestricted text should be able to deal with words that are not found in the MT lexicon. Without some kind of recognition, the parse may be incomplete, there is no transfer for the unfound word, and tests for transfers for surrounding words will often fail, resulting in poor translation. Interestingly, not much(More)
In the IBM LMT machine translation system, derivational morphological rules recognize and analyze words that are not found in its source lexicons, and generate default transfers for these unlisted words. Unfound words with no inflectional or derivational affixes are by default nouns. These rules are now expanded to provide lexical coverage of a particular(More)
We argue that many multi-word domain terms are not (and should not be regarded as) strictly atomic, especially from a parser’s point of view. We introduce the notion of Lexical Kernel Units (LKUs), and discuss some of their essential properties. LKUs are building blocks for lexicalizations of domain concepts, and as such, can be used for compositional(More)
Machine Translation (MT) systems that process unrestricted text should be able to deal with words that are not found in the MT lexicon. Without some kind of recognition, the parse may be incomplete, there is no transfer for the unfound word, and tests for transfers for surrounding words will often fail, resulting in poor translation. Interestingly, not much(More)
  • 1