Search Results for author:
Found 12 papers, 3 papers with code
UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference.
Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models.
Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion
In the field of text data augmentation, rule-based methods are widely adopted for real-world applications owing to their cost-efficiency.
Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
Our experimental results highlight the possibility of curriculum data augmentation for image data.
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation
Inspired by recent studies on decision boundaries, this paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models.
Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks
Offensive language detection is an important task for filtering out abusive expressions and improving online user experiences.
GPTs Are Multilingual Annotators for Sequence Generation Tasks
However, the conventional approach of data annotation through crowdsourcing is both time-consuming and expensive.
SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels
Rule-based text data augmentation is widely used for NLP tasks due to its simplicity.
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes
Text data augmentation is a complex problem due to the discrete nature of sentences.
Towards Robust Feature Learning with t-vFM Similarity for Continual Learning
Continual learning has been developed using standard supervised contrastive loss from the perspective of feature learning.
Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation
Understanding voluminous historical records provides clues on the past in various aspects, such as social and political issues and even natural science facts.
Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network
We note three points about training student model, caused by applying on-the-fly filter.
