View article

We propose a strongly lexicalist treatment of translation equivalence where mismatches due to diverging lexicalization patterns are dealt with by means of translation links which capture crosslinguistic generalizations across sets of semantically related lexical items. We show how this treatment can be developed within a unification-based, multilingual lexical knowledge base which is integrated with facilities for semi-automatic development of bilingual lexicons, and describe an approach to machine translation where generation difficulties arising from the lexicalist approach to complex transfer can be solved without making special assumptions about phrasal transfer.