To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation

• URL: http://arxiv.org/abs/2403.09259v2
• Date: Wed, 18 Dec 2024 17:18:12 GMT
• Title: To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation
• Abstract summary: Active learning (AL) techniques reduce labeling costs for training neural machine translation (NMT) models by selecting smaller representative subsets from unlabeled data for annotation.<n> Diversity sampling techniques select heterogeneous instances, while uncertainty sampling methods select instances with the highest model uncertainty.<n>We propose Hybrid Uncertainty and Diversity Sampling (HUDS), an AL strategy for domain adaptation in NMT that combines uncertainty and diversity for sentence selection.
• Score: 6.816044132563518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Active learning (AL) techniques reduce labeling costs for training neural machine translation (NMT) models by selecting smaller representative subsets from unlabeled data for annotation. Diversity sampling techniques select heterogeneous instances, while uncertainty sampling methods select instances with the highest model uncertainty. Both approaches have limitations - diversity methods may extract varied but trivial examples, while uncertainty sampling can yield repetitive, uninformative instances. To bridge this gap, we propose Hybrid Uncertainty and Diversity Sampling (HUDS), an AL strategy for domain adaptation in NMT that combines uncertainty and diversity for sentence selection. HUDS computes uncertainty scores for unlabeled sentences and subsequently stratifies them. It then clusters sentence embeddings within each stratum and computes diversity scores by distance to the centroid. A weighted hybrid score that combines uncertainty and diversity is then used to select the top instances for annotation in each AL iteration. Experiments on multi-domain German-English and French-English datasets demonstrate the better performance of HUDS over other strong AL baselines. We analyze the sentence selection with HUDS and show that it prioritizes diverse instances having high model uncertainty for annotation in early AL iterations.

Related papers

• Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification [4.909043927828085]
  Active learning aims to build high-quality labeled datasets by iteratively selecting the most informative samples from an unlabeled pool.<n>In fine-grained image classification, assessing this informativeness is especially challenging due to subtle inter-class differences.<n>We introduce a novel method, combining discrepancy-confusion uncertainty and calibration diversity for active fine-grained image classification (DECERN)<n>Our method achieves superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-29T02:03:44Z)
• DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning [54.35107462768146]
  Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. Existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. This paper proposes a novel dual-diversity enhancing and uncertainty-aware framework for CSAL.
  arXiv  Detail & Related papers  (2025-02-01T04:00:03Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples [9.360376286221943]
  We introduce an adaptive batch selection algorithm tailored to multi-label deep learning models. Our method converges faster and performs better than random batch selection.
  arXiv  Detail & Related papers  (2024-03-27T02:00:18Z)
• Dirichlet-Based Prediction Calibration for Learning with Noisy Labels [40.78497779769083]
  Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs) Existing approaches address this issue through loss correction or example selection methods. We propose the textitDirichlet-based Prediction (DPC) method as a solution.
  arXiv  Detail & Related papers  (2024-01-13T12:33:04Z)
• Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias [5.698050337128548]
  Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax prediction probabilities are often used as a confidence measure, although they are known to be overconfident, even for wrong predictions. We propose a novel confidence measure, called $mathcalT$-similarity, built upon the prediction diversity of an ensemble of linear classifiers.
  arXiv  Detail & Related papers  (2023-10-23T11:30:06Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data [69.30452751012568]
  We develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks.
  arXiv  Detail & Related papers  (2022-04-19T15:15:18Z)
• Active Learning by Feature Mixing [52.16150629234465]
  We propose a novel method for batch active learning called ALFA-Mix. We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions. We show that inconsistencies in these predictions help discovering features that the model is unable to recognise in the unlabelled instances.
  arXiv  Detail & Related papers  (2022-03-14T12:20:54Z)
• Gated recurrent units and temporal convolutional network for multilabel classification [122.84638446560663]
  This work proposes a new ensemble method for managing multilabel classification. The core of the proposed approach combines a set of gated recurrent units and temporal convolutional neural networks trained with variants of the Adam gradients optimization approach.
  arXiv  Detail & Related papers  (2021-10-09T00:00:16Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• Minimax Active Learning [61.729667575374606]
  Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. We develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner.
  arXiv  Detail & Related papers  (2020-12-18T19:03:40Z)
• Multi-Label Sampling based on Local Label Imbalance [7.355362369511579]
  Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. Existing multi-label sampling approaches alleviate the global imbalance of multi-label datasets. It is actually the imbalance level within the local neighbourhood of minority class examples that plays a key role in performance degradation.
  arXiv  Detail & Related papers  (2020-05-07T04:14:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.