Robust Probabilistic Predictive Syntactic Processing

Abstract

This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from left-to-right across the string. We argue that the parsing approach that we have adopted is well-motivated from a psycholinguistic perspective, as a model that captures probabilistic dependencies between lexical items, as part of the process of building connected syntactic structures. The basic parser and conditional probability models are presented, and empirical results are provided for its parsing accuracy on both newspaper text and spontaneous telephone conversations. Modifications to the probability model are presented that lead to improved performance. A new language model which uses the output of the parser is then defined. Perplexity and word error rate reduction are demonstrated over trigram models, even when the trigram is trained on significantly more data. Interpolation on a word-by-word basis with a trigram model yields additional improvements.

Ph.D. Thesis, Brown University, Advisor: Mark Johnson. 140 pages, 40 figures, 27 tables

References in corpus (10)

• An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
• Expoiting Syntactic Structure for Language Modeling
• Building Probabilistic Models for Natural Language
• Exploiting Syntactic Structure for Natural Language Modeling
• Precise n-gram Probabilities from Stochastic Context-free Grammars
• Memoization of Top Down Parsing
• Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser
• Recognition Performance of a Structured Language Model
• Measuring efficiency in high-accuracy, broad-coverage statistical parsing
• Refinement of a Structured Language Model