Módszerek összehasonlítása
Tekintse át a kiválasztott módszereket egymás mellett; az eltérő sorok kiemelve jelennek meg.
| Gyengén felügyelt mondatbeágyazások× | Gyengén felügyelt BERT-alapú osztályozás× | |
|---|---|---|
| Tudományterület | Mélytanulás | Mélytanulás |
| Módszercsalád | Machine learning | Machine learning |
| Keletkezés éve≠ | 2016–2019 | 2017–2020 |
| Megalkotó≠ | Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings) | Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration) |
| Típus≠ | Representation learning under weak supervision | Weakly supervised fine-tuning of pre-trained language model |
| Alapmű≠ | 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 ↗ | Meng, Y., Zhang, Y., Huang, J., Xiong, C., Ji, H., Zhang, C., & Han, J. (2020). Text Classification Using Label Names Only: A Language Model Self-Training Approach. Proceedings of EMNLP 2020, 9006–9017. link ↗ |
| Alternatív nevek | WS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddings | WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning |
| Kapcsolódó | 6 | 6 |
| Összefoglaló≠ | 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. | Weakly supervised BERT-based classification adapts BERT to text classification tasks when only noisy, heuristic, or programmatically generated labels are available instead of clean human annotations. It combines weak supervision frameworks — such as labeling functions and data programming — with BERT's pre-trained language representations to achieve robust classification without expensive hand-labeling. |
| ScholarGateAdatkészlet ↗ |
|
|