Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources

arXiv:2402.13302v1 Announce Type: new
Abstract: Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. Despite the recent introduction of Word Embeddings and Recurrent Neural Networks to design powerful context-related features, the interest in improving WSD models using Semantic Lexical Resources (SLRs) is mostly restricted to knowledge-based approaches. In this paper, we enhance "modern" supervised WSD models exploiting two popular SLRs: WordNet and WordNet Domains. We propose an effective way to introduce semantic …

abstract art arxiv benchmarks context cs.cl design embeddings features introduction modern networks neural networks popular recurrent neural networks resources semantic sense state type word word embeddings