An Application of WordNet to Prepositional Attachment

This paper presents a method for word sense disambiguation and coherence understanding of prepositional relations. The method relies on information provided by WordNet 1.5. We rst classify preposi-tional attachments according to semantic equivalence of phrase heads and then apply inferential heuristics for understanding the validity of prepositional structures. 1 Problem description In this paper, we address the problem of disam-biguation and understanding prepositional attachment. The arguments of prepositional relations are automatically categorized into semantically equivalent classes of WordNet (Miller and Teibel, 1991) concepts. Then by applying inferential heuristics on each class, we establish semantic connections between arguments that explain the validity of that prepositional structure. The method uses information provided by WordNet, such as semantic relations and textual glosses. We have collected prepositional relations from the Wall Street Journal tagged articles of the PENN TREEBANK. Here, we focus on preposition of, the most frequently used preposition in the corpus. 2 Classes of prepositional relations Since most of the prepositional attachments obey the principle of locality (Wertmer, 1991), we considered only the case of prepositional phrases preceded by noun or verb phrases. We scanned the corpus and ltered the phrase heads to create C, an ad hoc collection of sequences < noun prep noun > and < verb prep noun >. This collection is divided into classes of prepositional relations, using the following deenitions: Deenition 1: Two prepositional structures < noun 1 prep noun 2 > and < noun 3 prep noun 4 > belong to the same class if one of the following conditions holds: noun 1 , and noun 2 are hypernym/hyponym of noun 3 , and noun 4 respectively, or noun 1 , and noun 2 have a common hyper-nym/hyponym and with noun 3 , and noun 4 , respectively. A particular case is when noun 1 (noun 2) and noun 3 (noun 4) are synonyms. Deenition 2: Two prepositional structures < verb 1 prep noun 1 > and < verb 2 prep noun 2 > belong to the same class if one of the following conditions holds: verb 1 , and noun 1 are hypernym/hyponym of verb 2 , and noun 2 , respectively or verb 1 , and noun 1 have a common hyper-nym/hyponym with verb 2 , and noun 2 , respectively. A particular case is when the verbs or the nouns are synonyms, respectively. The main beneet and reason for grouping prepo-sitional relations into …