The following article presents an overview of the use of artificial neuralnetworks for the task of Word Sense Disambiguation (WSD). More specifically, itsurveys the advances in neural language models in recent years that have resultedin methods for the effective distributed representation of linguistic units. Suchrepresentations – word embeddings, context embeddings, sense embeddings – canbe effectively applied for WSD purposes, as they encode rich semantic information,especially in conjunction with recurrent neural networks, which are able to capturelong-distance relations encoded in word order, syntax, information structuring.
展开▼
