Word Sense Disambiguation (WSD) is a central task in the area of Natural Language Processing. In the past few years several context-based probabilistic and machine learning methods for WSD have been presented in literature. However, an important area of research that has not been given the attention it deserves is a formal analysis of the parameters affecting the performance of the learning task faced by these systems. Usually performance is estimated by measuring precision and recall of a specific algorithm for specific test sets and environmental conditions. Therefore, a comparison among different learning systems and an objective estimation of the difficulty of the learning task is extremely difficult.
In this paper we propose, in the framework of Computational Learning theory, a formal analysis of the relations between accuracy of a context-based WSD system, the complexity of the context representation scheme, and the environmental conditions (e.g. the complexity of language domain and concept inventory).
[1]
Russell Greiner,et al.
Computational learning theory and natural learning systems
,
1997
.
[2]
Leslie G. Valiant,et al.
A theory of the learnable
,
1984,
CACM.
[3]
Stephen José Hanson,et al.
Computational Learning Theory and Natural Learning
,
1996
.
[4]
Janyce Wiebe,et al.
Decomposable Modeling in Natural Language Processing
,
1999,
CL.
[5]
Martin Anthony,et al.
Computational learning theory: an introduction
,
1992
.
[6]
Umesh V. Vazirani,et al.
An Introduction to Computational Learning Theory
,
1994
.
[7]
Paola Velardi,et al.
Automatic Semantic Tagging of Unknown Proper Names
,
1998,
ACL.
[8]
Paola Velardi,et al.
Will Very Large Corpora Play For Semantic Disambiguation The Role That Massive Computing Power Is Playing For Other AI-Hard Problems?
,
2000,
LREC.