paper-with-me

홈 › Papers

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation

2022-12-16 · Yuxi Feng, Xiaoyuan Yi, Xiting Wang, Laks V. S. Lakshmanan, Xing Xie

Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of pre-trained language models when labeled data is insufficient. However, it remains challenging to incorporate ST into attribute-controllable language generation. Augmented by only self-generated pseudo text, generation models over-emphasize exploitation of the previously learned space, suffering from a constrained generalization boundary. We revisit ST and propose a novel method, DuNST to alleviate this problem. DuNST jointly models text generation and classification with a shared Variational AutoEncoder and corrupts the generated pseudo text by two kinds of flexible noise to disturb the space. In this way, our model could construct and utilize both pseudo text from given labels and pseudo labels from available unlabeled text, which are gradually refined during the ST process. We theoretically demonstrate that DuNST can be regarded as enhancing exploration towards the potential real text space, providing a guarantee of improved performance. Experiments on three controllable generation tasks show that DuNST could significantly boost control accuracy while maintaining comparable generation fluency and diversity against several strong baselines.

📄 PDF Abstract BibTeX arXiv:2212.08724

Code (1)

peterfengyx/dunst 공식 구현 pytorch

Tasks

AttributeDiversityText Generation

Similar Papers 제목 키워드 기반

Self-semi-supervised Learning to Learn from NoisyLabeled Data

2020-11-03 · Jiacheng Wang, Yue Ma, Shuang Gao

The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research …

Self-training with noisy student model and semi-supervised loss function for dcase 2021 challenge task 4

2021-07-06 · Nam Kyun Kim, Hong Kook Kim

This report proposes a polyphonic sound event detection (SED) method for the DCASE 2021 Challenge Task 4. The proposed SED model consists of two stages: a mean-teacher model for providing target labels regarding weakly l…

Event DetectionSound Event Detection

Semi-supervised Relation Extraction via Incremental Meta Self-Training

2020-10-06 · Findings (EMNLP) 2021 11 · Xuming Hu, Chenwei Zhang, Fukun Ma, Chenyao Liu 외

To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods s…

Meta-LearningPseudo LabelRelationRelation Classification+1

Dual Invariance Self-training for Reliable Semi-supervised Surgical Phase Recognition

2025-01-29 · Sahar Nasirihaghighi, Negin Ghamsarian, Raphael Sznitman, Klaus Schoeffmann

Accurate surgical phase recognition is crucial for advancing computer-assisted interventions, yet the scarcity of labeled data hinders training reliable deep learning models. Semi-supervised learning (SSL), particularly …

Pseudo LabelSurgical phase recognition

SELF: Learning to Filter Noisy Labels with Self-Ensembling

2019-10-04 · ICLR 2020 1 · Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen 외

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filter…

image-classificationImage ClassificationSelf-Learning