Confluent Preorder Parsing of Deterministic Grammars

Abstract

In this paper, syntactic parsing is discussed in the context of connectionism, a new model, the confluent preorder parser (CPP), is proposed which exemplifies the holistic parsing paradigm. Holistic parsing has the advantage that little knowledge has to be assumed concerning the detailed parsing algorithm. This algorithm is often unkown or debatable, especially when human language understanding is concerned. In the CPP, syntactic parsing is achieved by transforming from the connectionist representation of the sentence to the connectionist representation of the preorder traversal of its parse tree, instead of to the representation of the parse tree itself. As revealed by the simulation experiments, generalization performance is excellent (as high as 90%). Also, the CPP is capable of parsing erroneous sentences and resolving lexical category ambiguities. A systematic study is conducted to explore the range of factors which can affect the effectiveness of the system. The error-recovery capability is especially useful in natural language processing when incomplete or even ungrammatical sentences must be dealt with.

Keywords:

• Keywords: Neural Networks
• Connectionist Syntactic Parsing
• Raam
• Holistic Parsing
• Confluent Preorder Parser
• Linearization Of a Hierarchical Parse Tree
• Parsing Erroneous Sentences
• Lexical Category Disambiguation