The Use of Classifiers in Sequential Inference

TL;DR

This paper explores methods for combining multiple classifiers to improve sequential inference, introducing two approaches—Markovian models and constraint satisfaction extensions—and demonstrating their effectiveness in shallow parsing tasks.

Contribution

It presents two novel frameworks for classifier combination in sequential inference, extending HMMs and constraint satisfaction models with efficient algorithms.

Findings

Both approaches effectively combine classifiers for better inference.

Experimental results show improved shallow parsing accuracy.

The methods are adaptable to various structured prediction tasks.

Abstract

We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we develop two general approaches for an important subproblem-identifying phrase structure. The first is a Markovian approach that extends standard HMMs to allow the use of a rich observation structure and of general classifiers to model state-observation dependencies. The second is an extension of constraint satisfaction formalisms. We develop efficient combination algorithms under both models and study them experimentally in the context of shallow parsing.