A Connectionist Approach to Propositional Phrase Attachment for Real World Texts

Ill this paper we describe a neural network-based approach to prepositional phrase attachment disam-biguation for real world texts. Although the use of semantic classes in this task seems intuitively to be adequate, methods employed to date have not used them very effectively. Causes of their poor results are discussed. Our model, which uses only classes, scores appreciably better than the other class-based methods which have been tested on the Wall Street Journal corpus. To date, the best result obtained using only classes was a score of 79.1%; we obtained an accuracy score of 86.8%. This score is among the best reported in the literature using this corpus. 1 Introduction Structural ambiguity is one of the most serious problems faced by Natural Language Processing (NLP) systems. It occurs when the syntactic information does not suffice to make an assignment decision. Prepositional phrase (PP) attachment is, perhaps, the canonical case of structural ambiguity. What kind of information should we use in order to solve this ambiguity? In most cases, the information needed comes from a local context, and the attach-lnent decision is based essentially on the relationships existing between predicates and arguments, what Katz y Fodor (1963) called selectional restrictions. For example, in the expression: (V accommodate) (gP Johnson's election) (PP as a director), the PP is attached to the NP. However, in the expression: (V taking) (NP that news) (PP as a sign to be cautions), the PP is attached to the verb. In both expressions, the attachment site is decided on tile basis of verb and noun seleetional restrictions. In other eases, the information determining the PP attachment comes from a global context. In this paper we will focus on the disambiguation mechanism based on selectional restrictions. Previous work has shown that it is extremely difficult to build handmade rule-based systems able to deal with this kind of problem. Since such handmade systems proved unsuccessful, in recent years two main methods have appeared capable of auto-1233 matic learning from tagged corpora: automatic rule based methods and statistical methods. In this paper we will show that, providing that the problem is correctly approached, an NN can obtain better results than any of the methods used to date for PP attachment disambiguation. Statistical methods consider how a local context can disambiguate PP attachment estimating the probability from a corpus: p(verb attachlv NP1 prep NP2) Since an NP can be arbitrarily complex, the …