Publication | Closed Access

On the class separability of contextual embeddings representations – or “The classifier does not matter when the (text) representation is so good!”

Natural Language ProcessingEngineeringMachine LearningAutomatic ClassificationComputational LinguisticsWord EmbeddingsClass SeparabilityContent RepresentationLanguage StudiesDistributional SemanticsContextual Embeddings RepresentationsLinguisticsLanguage ProcessingText MiningRepresentation Learning