Módszerek összehasonlítása
Tekintse át a kiválasztott módszereket egymás mellett; az eltérő sorok kiemelve jelennek meg.
| Többnyelvű RoBERTa-alapú osztályozás× | BERT-alapú osztályozás× | |
|---|---|---|
| Tudományterület | Mélytanulás | Mélytanulás |
| Módszercsalád | Machine learning | Machine learning |
| Keletkezés éve≠ | 2020 | 2019 |
| Megalkotó≠ | Conneau, A. et al. (Facebook AI Research) | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language) |
| Típus≠ | Pretrained multilingual transformer fine-tuned for classification | Pre-trained language model with fine-tuning |
| Alapmű≠ | Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzman, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised Cross-lingual Representation Learning at Scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 8440–8451. DOI ↗ | 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 ↗ |
| Alternatív nevek | XLM-RoBERTa classification, mRoBERTa, cross-lingual RoBERTa classifier, multilingual transformer classification | BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS |
| Kapcsolódó | 4 | 4 |
| Összefoglaló≠ | Multilingual RoBERTa-based classification uses XLM-RoBERTa — a transformer pretrained on 100+ languages via masked language modeling — and fine-tunes it on labeled text to assign categories across multiple languages. By sharing a single model across languages, it enables robust cross-lingual and zero-shot text classification without needing separate per-language classifiers. | 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. |
| ScholarGateAdatkészlet ↗ |
|
|