Method evidence record
Semi-supervised BERT-based Classification
Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Semi-supervised BERT-based Text Classification
Taxonomic method record · ml-model / deep-learning
- Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792. · URL
- Chen, J., Yang, Z., & Yang, D. (2020). MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2147–2157. · DOI 10.18653/v1/2020.acl-main.194
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.