Comparative Experiments on Disambiguating Word Senses: An Illustration of the Role of Bias in Machine Learning

TL;DR

This study compares seven machine learning algorithms for word sense disambiguation, highlighting the impact of bias and showing statistical and neural-network methods perform best on the task.

Contribution

It provides an experimental comparison of diverse algorithms for word sense disambiguation and discusses the influence of bias on their performance.

Findings

Statistical and neural-network methods outperform others on disambiguating 'line' senses.

Bias plays a significant role in explaining differences in algorithm performance.

The paper emphasizes the importance of bias in machine learning for NLP tasks.

Abstract

This paper describes an experimental comparison of seven different learning algorithms on the problem of learning to disambiguate the meaning of a word from context. The algorithms tested include statistical, neural-network, decision-tree, rule-based, and case-based classification techniques. The specific problem tested involves disambiguating six senses of the word ``line'' using the words in the current and proceeding sentence as context. The statistical and neural-network methods perform the best on this particular problem and we discuss a potential reason for this observed difference. We also discuss the role of bias in machine learning and its importance in explaining performance differences observed on specific problems.