Similarity Based Label Smoothing For Dialogue Generation

• URL: http://arxiv.org/abs/2107.11481v1
• Date: Fri, 23 Jul 2021 23:25:19 GMT
• Title: Similarity Based Label Smoothing For Dialogue Generation
• Authors: Sougata Saha, Souvik Das, Rohini Srihari
• Abstract summary: Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Label smoothing enforces a data independent uniform distribution on the incorrect training targets, which leads to an incorrect assumption of equi-probable incorrect targets for each correct target. We propose to transform the uniform distribution of the incorrect target probabilities in label smoothing, to a more natural distribution based on semantics.
• Score: 1.1279808969568252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be achieved by using regularization techniques like label smoothing, which converts the training "hard" targets to "soft" targets. However, label smoothing enforces a data independent uniform distribution on the incorrect training targets, which leads to an incorrect assumption of equi-probable incorrect targets for each correct target. In this paper we propose and experiment with incorporating data dependent word similarity based weighing methods to transforms the uniform distribution of the incorrect target probabilities in label smoothing, to a more natural distribution based on semantics. We introduce hyperparameters to control the incorrect target distribution, and report significant performance gains over networks trained using standard label smoothing based loss, on two standard open domain dialogue corpora.

Related papers

• Overcoming label shift in targeted federated learning [8.223143536605248]
  Federated learning enables multiple actors to collaboratively train models without sharing private data. One common violation is label shift, where the label distributions differ across clients or between clients and the target domain. We propose FedPALS, a novel model aggregation scheme that adapts to label shifts by leveraging knowledge of the target label distribution at the central server.
  arXiv  Detail & Related papers  (2024-11-06T09:52:45Z)
• Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture [21.494268411607766]
  We propose an innovative label shift framework named as Aligned Distribution Mixture (ADM) Within this framework, we enhance four typical label shift methods by introducing modifications to the classifier training process. Considering the distinctiveness of the proposed one-step approach, we develop an efficient bi-level optimization strategy.
  arXiv  Detail & Related papers  (2024-11-04T12:51:57Z)
• Towards noise contrastive estimation with soft targets for conditional models [0.6138671548064356]
  We propose a loss function that is compatible with probabilistic targets. Our new soft target InfoNCE loss is conceptually simple, efficient to compute, and can be motivated through the framework of noise contrastive estimation. We observe that soft target InfoNCE performs on par with strong soft target cross-entropy baselines and outperforms hard target NLL and InfoNCE losses on popular benchmarks.
  arXiv  Detail & Related papers  (2024-04-22T10:45:59Z)
• Probabilistic Test-Time Generalization by Variational Neighbor-Labeling [62.158807685159736]
  This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. Probability pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. Variational neighbor labels that incorporate the information of neighboring target samples to generate more robust pseudo labels.
  arXiv  Detail & Related papers  (2023-07-08T18:58:08Z)
• Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation [16.878277421402945]
  We propose a regularization scheme that brings dynamic nature into the smoothing parameter. A model in training self-regulates the extent of smoothing on the fly during forward propagation.
  arXiv  Detail & Related papers  (2022-10-22T11:52:38Z)
• Generative multitask learning mitigates target-causing confounding [61.21582323566118]
  We propose a simple and scalable approach to causal representation learning for multitask learning. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. Our results on the Attributes of People and Taskonomy datasets reflect the conceptual improvement in robustness to prior probability shift.
  arXiv  Detail & Related papers  (2022-02-08T20:42:14Z)
• Diversifying Dialog Generation via Adaptive Label Smoothing [49.216146120454745]
  We propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts. Our approach outperforms various competitive baselines in producing diverse responses.
  arXiv  Detail & Related papers  (2021-05-30T14:41:09Z)
• Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation [14.050836886292869]
  We introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. We verify the effectiveness of such methods in the autonomous driving setting.
  arXiv  Detail & Related papers  (2021-04-06T16:07:22Z)
• Two-phase Pseudo Label Densification for Self-training based Domain Adaptation [93.03265290594278]
  We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD. In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images. In the second phase, we perform a confidence-based easy-hard classification. To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
  arXiv  Detail & Related papers  (2020-12-09T02:35:25Z)
• MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network [51.84251358009803]
  We present a novel self-supervised learning approach for conditional generative adversarial networks (GANs) under a semi-supervised setting. We perform augmentation by randomly sampling sensible labels from the label space of the few labelled examples available. Our method surpasses the baseline with only 20% of the labelled examples used to train the baseline.
  arXiv  Detail & Related papers  (2020-06-11T17:14:55Z)
• Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation [49.295165476818866]
  This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. This paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning.
  arXiv  Detail & Related papers  (2020-03-08T12:37:19Z)

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.