השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| Doc2Vec מותאם-תחום× | סיווג מבוסס BERT אדפטיבי לתחום× | |
|---|---|---|
| תחום | למידה עמוקה | למידה עמוקה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2014 (Doc2Vec); domain-adaptive application mid-2010s onward | 2019–2020 |
| הוגה השיטה≠ | Le & Mikolov (Doc2Vec); domain adaptation literature (Blitzer, Daumé III, and others) | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT |
| סוג≠ | Unsupervised / domain-adaptive document embedding | Domain-adaptive pre-training followed by supervised fine-tuning |
| מקור מכונן≠ | Le, Q. V., & Mikolov, T. (2014). Distributed representations of sentences and documents. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), PMLR 32(2), 1188–1196. link ↗ | 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 ↗ |
| כינויים | domain-adapted Doc2Vec, cross-domain paragraph vector, domain-adaptive PV-DM, domain-adaptive PV-DBOW | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT |
| קשורות≠ | 5 | 6 |
| תקציר≠ | Domain-adaptive Doc2Vec adapts the Paragraph Vector (Doc2Vec) framework so that document embeddings learned on a source domain transfer effectively to a target domain. By aligning the representation space across domains during or after training, the model produces embeddings that are informative on both, enabling cross-domain classification, sentiment analysis, and retrieval with limited target-domain labels. | 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. |
| ScholarGateמערך נתונים ↗ |
|
|