Few Shot Text Classification
Related Papers
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification
AbstractA recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained language model and …...
Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network
AbstractIn this paper, we propose a new few-shot text classification method. Compared with supervised learning methods which require a large corpus of labeled documents, our method aims to make it …...
Don’t Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification
Increasing studies leverage pre-trained lan- guage models and meta-learning frameworks to solve few-shot text classification problems. Most of the current studies focus on building a meta-learner from the information of …...
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
AbstractFew-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. …...
Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification
AbstractFew-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect …...
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
AbstractPrompt-based learning (i.e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model. In this paper, we propose Automatic Multi-Label Prompting (AMuLaP), a simple yet effective …...
EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency Regularization
AbstractWhile the prompt-based fine-tuning methods had advanced few-shot natural language understanding tasks, self-training methods are also being explored. This work revisits the consistency regularization in self-training and presents explicit and …...
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
AbstractRecent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates. Similar attempts have been made on named entity recognition (NER) which manually design …...
Noisy Channel Language Model Prompting for Few-Shot Text Classification
AbstractWe introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel …...
Prompt-Based Meta-Learning For Few-shot Text Classification
AbstractFew-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances. Current meta-learning methods have achieved satisfying results in various few-shot situations. Still, they …...
Sentence-aware Adversarial Meta-Learning for Few-Shot Text Classification
AbstractMeta-learning has emerged as an effective approach for few-shot text classification. However, current studies fail to realize the importance of the semantic interaction between sentence features and neglect to enhance …...