A Knowledge-Based Approach to Word Sense Disambiguation by distributional selection and semantic features

TL;DR

This paper presents a knowledge-based word sense disambiguation method that uses distributional selection and semantic features, achieving 78% accuracy on French corpus data with BabelNet.

Contribution

It introduces a combinatorial optimization approach for sense disambiguation based on distributional selection and semantic features, improving efficiency over exhaustive pairwise comparisons.

Findings

Achieved 78% accuracy on French corpus data

Demonstrated effectiveness of combinatorial optimization in WSD

Utilized BabelNet for semantic network integration

Abstract

Word sense disambiguation improves many Natural Language Processing (NLP) applications such as Information Retrieval, Information Extraction, Machine Translation, or Lexical Simplification. Roughly speaking, the aim is to choose for each word in a text its best sense. One of the most popular method estimates local semantic similarity relatedness between two word senses and then extends it to all words from text. The most direct method computes a rough score for every pair of word senses and chooses the lexical chain that has the best score (we can imagine the exponential complexity that returns this comprehensive approach). In this paper, we propose to use a combinatorial optimization metaheuristic for choosing the nearest neighbors obtained by distributional selection around the word to disambiguate. The test and the evaluation of our method concern a corpus written in French by means of the semantic network BabelNet. The obtained accuracy rate is 78 % on all names and verbs chosen for the evaluation.