ScholarGate
Assistant

Comparer des méthodes

Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.

Embeddings de phrases faiblement supervisées×Classification par BERT sous supervision faible×
DomaineApprentissage profondApprentissage profond
FamilleMachine learningMachine learning
Année d'origine2016–20192017–2020
Auteur d'origineRatner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings)Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)
TypeRepresentation learning under weak supervisionWeakly supervised fine-tuning of pre-trained language model
Source fondatriceRatner, 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 ↗
AliasWS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddingsWS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning
Apparentées66
RésuméWeakly 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.
ScholarGateJeu de données
  1. v1
  2. 2 Sources
  3. PUBLISHED
  1. v1
  2. 2 Sources
  3. PUBLISHED

Aller à la recherche Télécharger les diapositives

ScholarGateComparer des méthodes: Weakly supervised sentence embeddings · Weakly supervised BERT-based classification. Consulté le 2026-06-15 sur https://scholargate.app/fr/compare