Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing

by   Clara Meister, et al.

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common sign of overfitting. This class of techniques, of which label smoothing is one, has a connection to entropy regularization. Despite the consistent success of label smoothing across architectures and data sets in language generation tasks, two problems remain open: (1) there is little understanding of the underlying effects entropy regularizers have on models, and (2) the full space of entropy regularization techniques is largely unexplored. We introduce a parametric family of entropy regularizers, which includes label smoothing as a special case, and use it to gain a better understanding of the relationship between the entropy of a model and its performance on language generation tasks. We also find that variance in model performance can be explained largely by the resulting entropy of the model. Lastly, we find that label smoothing provably does not allow for sparsity in an output distribution, an undesirable property for language generation models, and therefore advise the use of other entropy regularization methods in its place.


page 7

page 8

page 16


Does label smoothing mitigate label noise?

Label smoothing is commonly used in training deep learning models, where...

Regularizing Neural Networks by Penalizing Confident Output Distributions

We systematically explore regularizing neural networks by penalizing low...

An Investigation of how Label Smoothing Affects Generalization

It has been hypothesized that label smoothing can reduce overfitting and...

Capturing Label Distribution: A Case Study in NLI

We study estimating inherent human disagreement (annotation label distri...

Similarity Based Label Smoothing For Dialogue Generation

Generative neural conversational systems are generally trained with the ...

Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative

In this paper, we study several GAN related topics mathematically, inclu...

Deep Residual Output Layers for Neural Language Generation

Many tasks, including language generation, benefit from learning the str...