Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser

TL;DR

This paper introduces an efficient bottom-up parser that interleaves syntax and semantics, employing techniques to reduce ambiguity and improve parsing speed, with demonstrated robustness in speech recognition accuracy.

Contribution

It presents novel techniques for reducing local ambiguity in bottom-up parsing by interleaving syntax and semantics, leading to faster and more robust parsing.

Findings

Significant reduction in chart-edges and parsing time.

Improved speech recognizer accuracy.

Effective ambiguity reduction techniques.

Abstract

We describe an efficient bottom-up parser that interleaves syntactic and semantic structure building. Two techniques are presented for reducing search by reducing local ambiguity: Limited left-context constraints are used to reduce local syntactic ambiguity, and deferred sortal-constraint application is used to reduce local semantic ambiguity. We experimentally evaluate these techniques, and show dramatic reductions in both number of chart-edges and total parsing time. The robust processing capabilities of the parser are demonstrated in its use in improving the accuracy of a speech recognizer.