Smoothing and Word Sense Disambiguation

This paper presents an algorithm to apply the smoothing techniques described in [1] to three different Machine Learning (ML) methods for Word Sense Disambiguation (WSD). The method to obtain better estimations for the features is explained step by step, and applied to n-way ambiguities. The results obtained in the Senseval-2 framework show that the method can help improve the precision of some weak learners, and in combination attain the best results so far in this setting.

• Type: Conference
• Year: 2004
• Where: TAL
• Authors: Eneko Agirre, David Martínez
• Keywords: Better Estimations, Natural Language Processing, Smoothing Techniques, TAL 2004, Word Sense Disambiguation