Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| Embeddings di frasi supervisionati debolmente× | Apprendimento per trasferimento con embedding di frasi× | |
|---|---|---|
| Campo | Apprendimento profondo | Apprendimento profondo |
| Famiglia | Machine learning | Machine learning |
| Anno di origine≠ | 2016–2019 | 2017–2019 |
| Ideatore≠ | Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings) | Reimers, N. & Gurevych, I. (SBERT); Conneau, A. et al. (InferSent) |
| Tipo≠ | Representation learning under weak supervision | Transfer learning / sentence representation |
| Fonte seminale≠ | Ratner, A., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗ | 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 ↗ |
| Alias | WS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddings | sentence embedding transfer learning, pre-trained sentence encoder fine-tuning, SBERT transfer learning, sentence representation transfer |
| Correlati≠ | 6 | 5 |
| Sintesi≠ | Weakly supervised sentence embeddings train dense sentence representations using noisy, heuristic, or programmatically generated labels instead of costly human annotation. Labeling functions — rules, distant supervision signals, or lightweight classifiers — supply approximate supervision that a label model aggregates into probabilistic labels, which then guide the sentence encoder to produce task-useful representations at scale. | 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. |
| ScholarGateInsieme di dati ↗ |
|
|