Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach

Abstract

Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the finetuning stage. We study the problem of finetuning pre-trained LMs using only weak supervision, without any labeled data. This problem is challenging because the high capacity of LMs makes them prone to overfitting the noisy labels generated by weak supervision. To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision. Underpinned by contrastive regularization and confidence-based reweighting, our framework gradually improves model fitting while effectively suppressing error propagation. Experiments on sequence, token, and sentence pair classification tasks show that our model outperforms the strongest baseline by large margins and achieves competitive performance with fully-supervised fine-tuning methods. Our implementation is available on https:// github.com/yueyu1030/COSINE.

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

“…Our work is also relevant to semi-supervised learning, where the training data is only partially labeled. There have been many semisupervised learning methods, including the popular self-training methods used in our experiments for comparison (Yarowsky, 1995;Rosenberg et al, 2005;Tarvainen and Valpola, 2017;Miyato et al, 2018;Meng et al, 2018;Clark et al, 2018;Yu et al, 2021). Different from weak supervision, these semi-supervised learning methods usually has a partial set of labeled data.…”

“…One potential future direction is to combine NEE-DLE with other fully weakly supervised / semisupervised learning techniques to further improve the performance, e.g., contrastive regularization (Yu et al, 2021).…”

Scellseg: a style-aware cell instance segmentation tool with pre-training and contrastive fine-tuning

“…Specifically, the work achieved three main innovations: Firstly, we refined the architecture of Cellpose through introducing attention mechanisms and hierarchical information, making the model more sensitive to different styles. Secondly, we implemented a contrastive fine-tuning strategy to leverage the information from both unlabelled and pre-trained data based on contrastive learning, which have also achieved great success in other deep learning applications [28][29][30][31][32] . Finally, we organized three benchmarking datasets containing three levels of cell images for further use in segmentation algorithm development.…”

WRENCH: A Comprehensive Benchmark for Weak Supervision

“…To reduce the efforts of annotation, recent weak supervision (WS) frameworks have been proposed which focus on enabling users to leverage a diversity of weaker, often programmatic supervision sources [76,77,75] to label and manage training data in an efficient way. Recently, WS has been widely applied to various machine learning tasks in a diversity of domains: scene graph prediction [9], video analysis [23,92], image classification [12], image segmentation [35], autonomous driving [96], relation extraction [36,107,57], named entity recognition [82,53,50,45,27], text classification [78,100,85,86], dialogue system [63], biomedical [43,19,64], healthcare [20,17,21,80,93,81], software engineering [74], sensors data [24,39], E-commerce [66,103], and multi-agent systems [102].…”

“…These two-stage methods mainly focus on the efficiency and effectiveness of the label model, while maintaining the maximal flexibility of the end model. Recent approaches have also focused on integrating semi-or self-supervised approaches [100]; we view these as modified end models in our benchmarking framework. In addition to these two-stage methods, researchers have also explored the possibility of coupling the label model and the end model in an end-to-end manner [78,45,38].…”