Transductive Auxiliary Task Self-Training for Neural Multi-Task Models
Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task self-training: training a multi-task model on (i) a combination of main and auxiliary task training data, and (ii) test instances with auxiliary task labels which a single-task version of the model has previously generated. We perform extensive experiments on 86 combinations of languages and tasks. Our results are that, on average, transductive auxiliary task self-training improves absolute accuracy by up to 9.56% over the pure multi-task model for dependency relation tagging and by up to 13.03% for semantic tagging.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Task LearningSimilar Papers 제목 키워드 기반
Semi-Supervised SAR ATR Framework with Transductive Auxiliary Segmentation
Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training dat…
Few-Shot LearningInductive BiasSegmentationTransductive Multi-view Zero-Shot Learning
Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no ann…
Transfer LearningZero-Shot LearningTransductive Multi-class and Multi-label Zero-shot Learning
Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed t…
Multi-label zero-shot learningTransductive LearningTransfer LearningZero-Shot LearningTransductive image segmentation: Self-training and effect of uncertainty estimation
Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some a…
Image SegmentationMedical Image AnalysisMedical Image SegmentationSegmentation+2Composite Learning for Robust and Effective Dense Predictions
Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while …
Boundary DetectionDepth EstimationMonocular Depth EstimationMulti-Task Learning+2