Emergent Linguistic Rules from Inducing Decision Trees: Disambiguating Discourse Clue Words

TL;DR

This paper demonstrates how decision tree induction, combined with genetic algorithms, can automatically generate linguistically meaningful rules for disambiguating discourse clue words.

Contribution

It introduces a novel approach that uses decision trees and genetic algorithms to induce linguistically viable rules for discourse clue word sense disambiguation.

Findings

Decision trees produce linguistically viable disambiguation rules.

Genetic algorithms optimize the partitioning process.

The method improves automatic rule induction for discourse analysis.

Abstract

We apply decision tree induction to the problem of discourse clue word sense disambiguation with a genetic algorithm. The automatic partitioning of the training set which is intrinsic to decision tree induction gives rise to linguistically viable rules.