ScholarGate
Msaidizi
Machine learningDeep learning / NLP / CV

Uainishaji unaotegemea usimamizi dhaifu wa BERT

Uainishaji unaotegemea usimamizi dhaifu wa BERT hubadilisha BERT kwa ajili ya kazi za uainishaji wa maandishi wakati tu lebo zenye kelele, za mbinu, au zilizozalishwa kwa programu zinapatikana badala ya maelezo safi ya binadamu. Unachanganya mifumo ya usimamizi dhaifu — kama vile utendaji wa kuweka lebo na programu za data — na uwakilishi wa lugha uliotangulizwa awali wa BERT ili kufikia uainishaji thabiti bila kuandika kwa gharama kubwa.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

Vyanzo

  1. 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
  2. Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid Training Data Creation with Weak Supervision. Proceedings of the VLDB Endowment, 11(3), 269–282. DOI: 10.14778/3157794.3157797

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Weakly Supervised BERT-based Text Classification. ScholarGate. https://scholargate.app/sw/deep-learning/weakly-supervised-bert-based-classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Imerejelewa na

ScholarGateWeakly supervised BERT-based classification (Weakly Supervised BERT-based Text Classification). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/weakly-supervised-bert-based-classification · Seti ya data: https://doi.org/10.5281/zenodo.20539026