Continual Few-Shot Learning for Text Classification
Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle numbers, perform coreference, etc. Our solutions to complex problems are still far from perfect, so it is important to create systems that can learn to correct mistakes quickly, incrementally, and with little training data. In this work, we propose a continual few-shot learning (CFL) task, in which a system is challenged with a difficult phenomenon and asked to learn to correct mistakes with only a few (10 to 15) training examples. To this end, we first create benchmarks based on previously annotated data: two NLI (ANLI and SNLI) and one sentiment analysis (IMDB) datasets. Next, we present various baselines from diverse paradigms (e.g., memory-aware synapses and Prototypical networks) and compare them on few-shot learning and continual few-shot learning setups. Our contributions are in creating a benchmark suite and evaluation protocol for continual few-shot learning on the text classification tasks, and making several interesting observations on the behavior of similarity-based methods. We hope that our work serves as a useful starting point for future work on this important topic.
Code (1)
Tasks
Classificationcontinual few-shot learningFew-Shot LearningNatural Language InferenceSentiment Analysistext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Re-Evaluating Continual Learning with Few-Shot Adaptation
Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance o…
Image ClassificationContinual LearningLearning to Learn for Few-shot Continual Active Learning
Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting…
Active LearningContinual LearningMeta-Learningtext-classification+1Continual Learning Improves Zero-Shot Action Recognition
Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and le…
Action RecognitionContinual LearningZero-Shot Action RecognitionZero-Shot LearningAutomating Continual Learning
General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments. Conventional learning algorithms for neural networks, however, suffer from catastrophic forgetting (CF) -- p…
Continual Learningimage-classificationImage ClassificationMeta-Learning+1Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification
Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently. While in-context learning (ICL) with large language models (LLMs) has achie…
Contrastive Learningfew-shot-htcFew-shot HTCFew-Shot Learning+7