Sequential Model Selection for Word Sense Disambiguation

TL;DR

This paper introduces a sequential model selection approach for word sense disambiguation, systematically searching for the best feature interactions to improve probabilistic classifiers.

Contribution

It expands model selection methodology and provides the first comparative analysis of search strategies and evaluation criteria for this task.

Findings

Model selection improves disambiguation accuracy

Different search strategies vary in effectiveness

Evaluation criteria impact model performance

Abstract

Statistical models of word-sense disambiguation are often based on a small number of contextual features or on a model that is assumed to characterize the interactions among a set of features. Model selection is presented as an alternative to these approaches, where a sequential search of possible models is conducted in order to find the model that best characterizes the interactions among features. This paper expands existing model selection methodology and presents the first comparative study of model selection search strategies and evaluation criteria when applied to the problem of building probabilistic classifiers for word-sense disambiguation.