Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System
Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.
Code (1)
Tasks
ClassificationFew-Shot Text ClassificationGeneral Classificationintent-classificationIntent ClassificationRelation Classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation
The goal of incremental Few-shot Semantic Segmentation (iFSS) is to extend pre-trained segmentation models to new classes via few annotated images without access to old training data. During incrementally learning novel …
Few-Shot Semantic SegmentationSemantic SegmentationiDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-backgrou…
Continual LearningMedical Object Detectionobject-detectionObject DetectionASP-based Multi-shot Reasoning via DLV2 with Incremental Grounding
DLV2 is an AI tool for Knowledge Representation and Reasoning which supports Answer Set Programming (ASP) - a logic-based declarative formalism, successfully used in both academic and industrial applications. Given a log…
Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning
In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as lab…
In-Context LearningMulti-class ClassificationRerankingTranslationIncrementally Zero-Shot Detection by an Extreme Value Analyzer
Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen cl…
class-incremental learningClass Incremental LearningIncremental Learningobject-detection+2