Integration of Semantic and Syntactic Constraints for Structural Noun Phrase Disambiguation

A fundamental problem in Natural Language Processing is the integration of syntactic and semantic constraints. In this paper we describe a new approach for the integration of syntactic and semantic constraints which takes advantage of a learned memory model. Our model combines localist representations for the integration of constraints and distributed representations for learning semantic constraints. We apply this model to the problem of structural disambiguation of noun phrases and show that a learned connectionist model can scale up the underlying memory of a Natural Language Processing system. 1 Introduction The structural and semantic understanding of noun phrases and prepositional phrases is one of the most important tasks for natural language processing systems. Lately issues of prepositional phrase attachment have been addressed in different systems for sentence understanding (e.g. John and McClelland 88]). These systems focus on deciding whether a prepositional phrase attaches to a verb phrase or a noun phrase, for instance [Wilks et al. 85]: dictive verbal knowledge. However, attachment decisions for multiple prepositional phrases have to rely on syntactic and semantic knowledge associated with nouns and prepositions as well. The importance of this knowledge about nouns and prepositions is very obvious for the attachment decisions in isolated noun phrases, as for example in titles of scientific articles. In this paper we restrict our efforts to prepositional attachment in noun phrases using a corpus of titles and scientific articles from the physical sciences, for instance: Forces on charged particles of a plasma in a cavity res-onator. Irregularities in the drag effects on sputniks. We describe a two-level architecture for integrating syntactic and semantic constraints to disambiguate PP-attachment in noun phrases. The bottom level consists of backpropagation networks using distributed representations for the semantic relationships between nouns and prepositions. The backpropagation networks are trained with examples of these prepositional relationships for each preposition, so that the backpropagation networks learn the underlying semantic constraints. The top level consists of a relaxation network using localist representations for the integration of syntactic constraints with the learned semantic constraints. This approach allows the disambiguation of noun phrases which the system has not been trained on. 2 Noun Features for Prepositional Relationships Prepositional relationships depend on domain-specific features of the involved nouns. The noun phrases for our experiments were taken from the NPL corpus [Sparck-Jones 76] which contains article titles for scientific and technical domains. Typical examples in the corpus are: Pulse techniques for …