Anaphora Resolution, Collocations and Translation

Collocation identification and anaphora resolution are widely recognized as major issues for natural language processing, and particularly for machine translation. This paper focuses on their intersection domain, that is verb-object collocations in which the object has been pronominalized. To handle such cases, an anaphora resolution procedure must link the direct object pronoun to its antecedent. The identification of a collocation can then be made on the basis of the verb and its object or its antecedent. Preliminary results obtained from the translation of a large corpus will be discussed.