Uporedite metode
Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.
| Domenski-prilagođena klasifikacija zasnovana na BERT× | Ugrađivanje rečenica× | |
|---|---|---|
| Oblast | Duboko učenje | Duboko učenje |
| Porodica | Machine learning | Machine learning |
| Godina nastanka≠ | 2019–2020 | 2015–2019 |
| Tvorac≠ | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT | Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019) |
| Tip≠ | Domain-adaptive pre-training followed by supervised fine-tuning | Representation learning / embedding |
| Temeljni izvor≠ | Gururangan, S., Marasovic, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 8342–8360. DOI ↗ | 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), 3980–3990. DOI ↗ |
| Drugi nazivi | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT | sentence vectors, sentence representations, SBERT, semantic sentence encoding |
| Srodne≠ | 6 | 4 |
| Sažetak≠ | Domain-adaptive BERT-based classification extends the standard fine-tuning pipeline by first continuing BERT's masked-language-model pre-training on a large corpus of in-domain unlabeled text, then fine-tuning the adapted model on labeled examples for the target classification task. This two-stage approach closes the vocabulary and distributional gap between BERT's general pre-training corpus and specialized domains such as biomedicine, law, finance, or social-media text. | Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines. |
| ScholarGateSkup podataka ↗ |
|
|