Contrastive Bootstrapping for Label Refinement
Traditional text classification typically categorizes texts into pre-defined coarse-grained classes, from which the produced models cannot handle the real-world scenario where finer categories emerge periodically for accurate services. In this work, we investigate the setting where fine-grained classification is done only using the annotation of coarse-grained categories and the coarse-to-fine mapping. We propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages. During clustering, it pulls away negative passage-prototype pairs under the guidance of the mapping from both global and local perspectives. Experiments on NYT and 20News show that our method outperforms the state-of-the-art methods by a large margin.
Code (1)
Tasks
Clusteringtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition
Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing litera…
Contrastive LearningMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label Image RecognitionCross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrapping
Heterogeneous graph neural networks can represent information of heterogeneous graphs with excellent ability. Recently, self-supervised learning manner is researched which learns the unique expression of a graph through …
Contrastive LearningGraph Neural NetworkSelf-Supervised LearningLabel Refinement via Contrastive Learning for Distantly-Supervised Named Entity Recognition
Distantly-supervised named entity recognition (NER) locates and classifies entities using only knowledge bases and unlabeled corpus to mitigate the reliance on human-annotated labels. The distantly annotated data suffer …
Contrastive Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning
Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e., they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the…
Contrastive LearningRepresentation LearningTowards Unsupervised Deep Graph Structure Learning
In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the origina…
Contrastive LearningGraph structure learningNode Classification