Comparar métodos
Examine os métodos selecionados lado a lado; as linhas que diferem ficam destacadas.
| Aprendizagem por Transferência com Embeddings de Sentenças× | Classificação baseada em BERT× | |
|---|---|---|
| Área | Aprendizado profundo | Aprendizado profundo |
| Família | Machine learning | Machine learning |
| Ano de origem≠ | 2017–2019 | 2019 |
| Autor original≠ | Reimers, N. & Gurevych, I. (SBERT); Conneau, A. et al. (InferSent) | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language) |
| Tipo≠ | Transfer learning / sentence representation | Pre-trained language model with fine-tuning |
| Fonte seminal≠ | Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3982–3992. link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| Outros nomes | sentence embedding transfer learning, pre-trained sentence encoder fine-tuning, SBERT transfer learning, sentence representation transfer | BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS |
| Relacionados≠ | 5 | 4 |
| Resumo≠ | Transfer Learning with Sentence Embeddings takes a large pre-trained encoder — such as Sentence-BERT or the Universal Sentence Encoder — that already encodes general language knowledge into fixed-length vectors, and adapts it to a new task or domain with little additional labelled data. The pre-trained representations give a head start that often outperforms task-specific models trained from scratch on modest corpora. | BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data. |
| ScholarGateConjunto de dados ↗ |
|
|