Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Kratko-primjerska klasifikacija teksta× | BERT Embeddings× | |
|---|---|---|
| Područje | Rudarenje teksta | Rudarenje teksta |
| Obitelj | Process / pipeline | Process / pipeline |
| Godina nastanka≠ | — | 2019 |
| Tvorac≠ | — | Devlin, Chang, Lee & Toutanova (Google AI) |
| Vrsta≠ | NLP text-classification task (low-resource) | Contextual transformer text-representation method |
| Temeljni izvor≠ | Gao, T., Fisch, A. & Chen, D. (2021). Making Pre-trained Language Models Better Few-shot Learners. ACL. DOI ↗ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186. DOI ↗ |
| Drugi nazivi≠ | few-shot learning for text, Az Atışlı Metin Sınıflandırma (Few-Shot) | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri |
| Srodne | 4 | 4 |
| Sažetak≠ | Few-shot text classification assigns documents to classes using only a handful of labelled examples per class. Building on advances by Gao et al. (2021) and the prompt-free SetFit approach of Tunstall et al. (2022), it leans on prototypical networks, MAML, or fine-tuning of a large pretrained model to learn from scarce labels. | BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA. |
| ScholarGateSkup podataka ↗ |
|
|