Results 11 to 20 of about 9,001,538 (255)

Self-Training with Weak Supervision [PDF]

open access: yesProceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021
Accepted to NAACL 2021 (Long Paper)
Giannis Karamanolakis   +3 more
openaire   +2 more sources

Discriminative Self-Training for Punctuation Prediction [PDF]

open access: yesInterspeech 2021, 2021
Accepted by INTERSPEECH ...
Qian Chen 0003   +3 more
openaire   +3 more sources

Doubly-Robust Self-Training

open access: yesAdvances in Neural Information Processing Systems 36, 2023
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels.
Banghua Zhu   +6 more
openaire   +4 more sources

Enhancing Self-Training Methods

open access: yesCoRR, 2023
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that occurs when the student model repeatedly overfits to incorrect pseudo-labels given by the teacher model for the ...
Aswathnarayan Radhakrishnan   +5 more
openaire   +3 more sources

Confidence Regularized Self-Training [PDF]

open access: yes2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019
Accepted to ICCV 2019 (Oral)
Yang Zou 0003   +4 more
openaire   +3 more sources

Self-Training with Differentiable Teacher

open access: yesFindings of the Association for Computational Linguistics: NAACL 2022, 2022
NAACL 2022 (Findings)
Simiao Zuo   +7 more
openaire   +3 more sources

Unsupervised Controllable Generation with Self-Training [PDF]

open access: yes2021 International Joint Conference on Neural Networks (IJCNN), 2021
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically interpretable and disentangled factors of variation.
Chrysos, Grigorios G.   +3 more
openaire   +5 more sources

Self-training for biomedical parsing [PDF]

open access: yesProceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08, 2008
Parser self-training is the technique of taking an existing parser, parsing extra data and then creating a second parser by treating the extra data as further training data. Here we apply this technique to parser adaptation. In particular, we self-train the standard Charniak/Johnson Penn-Treebank parser using unlabeled biomedical abstracts.
David McClosky, Eugene Charniak
openaire   +2 more sources

Deep Bayesian Self-Training [PDF]

open access: yesNeural Computing and Applications, 2019
Supervised Deep Learning has been highly successful in recent years, achieving state-of-the-art results in most tasks. However, with the ongoing uptake of such methods in industrial applications, the requirement for large amounts of annotated data is often a challenge.
Fabio De Sousa Ribeiro   +5 more
openaire   +4 more sources

The effect of assertiveness training on self-efficacy among Iranian high school female students [PDF]

open access: yes, 2014
The current study considers the effect of assertiveness on the first-grade high school female students’ self-efficacy. The research method is quasi-experimental and the design is pretest posttest with control group.
Nikoogoftar, Mansooreh   +1 more
core   +3 more sources

Home - About - Disclaimer - Privacy