A Rule-Based and MT-Oriented Approach to Prepositional Phrase Attachment

Prepositional Phrase is the key issue in structural ambiguity. Recently, researches in corpora provide the lexical cue of prepositions with other words and the information could be used to partly resolve ambiguity resulted from prepositional phrases. Two possible attachments are considered in the literature: either noun attachment or verb attachment. In this paper, we consider the problem from viewpoint of machine translation. Four diierent attachments are told out according to their functionality: noun attachment, verb attachment, sentence-level attachment, and predicate-level attachment. Both lexical knowledge and semantic knowledge are involved resolving attachment in the proposed mechanism. Experimental results show that considering more types of prepositional phrases is useful in machine translation.