Tuning pre-trained language models (PLMs) with task-specific prompts has been a
promising approach for text classification. Particularly, previous studies suggest that prompt …

Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

We present a self-supervised learning framework, COCO-LM, that pretrains Language
Models by COrrecting and COntrasting corrupted text sequences. Following ELECTRA-style …

Text classification results can be hindered when just the bag-of-words model is used for
representing features, because it ignores word order and senses, which can vary with the …

Large language models (LLMs) excel in many diverse applications beyond language
generation, eg, translation, summarization, and sentiment analysis. One intriguing …

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 …

Topic models have been the prominent tools for automatic topic discovery from text corpora.
Despite their effectiveness, topic models suffer from several limitations including the inability …

Prompt learning approaches have made waves in natural language processing by inducing
better few-shot performance while they still follow a parametric-based learning paradigm; …

We study the problem of training named entity recognition (NER) models using only distantly-
labeled data, which can be automatically obtained by matching entity mentions in the raw …

Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity
on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set …