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

作者：Cláudio Moisés Valiense de Andrade, Fabiano Muniz Belém, Washington Luiz Miranda da Cunha, Celso Aparecido de França, Felipe Augusto Resende Viegas, Leonardo Rocha, Marcos André Gonçalves · 发表于：Information Processing & Management · 年份：2023 · DOI：10.1016/j.ipm.2023.103336 · 被引用次数：33 · 研究领域：Topic Modeling、Text and Document Classification Technologies、Natural Language Processing Techniques