Papers with word dropout
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing methods for data augmentation for text-based tasks such as machine translation are limited due to noise and noise. |
| Approach: | They propose a data augmentation policy with desirable properties as an optimization problem and propose 'SwitchOut' switchout randomly replaces words in both the source and target sentences with other random words from their corresponding vocabularies. |
| Outcome: | The proposed method outperforms strong alternatives such as word dropout on three translation datasets. |
Token Drop mechanism for Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Neural machine translation models are vulnerable to unfamiliar inputs. |
| Approach: | They propose to drop tokens of the input sentences to improve generalization and avoid overfitting for the NMT model. |
| Outcome: | The proposed approach improves on Chinese-English and English-Romanian benchmarks and achieves significant performance improvements over baselines. |
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs. |
| Approach: | They propose to use the variational autoencoder (VAE) for probabilistic sentence generation . they propose a variant of WAE that encourages the stochasticity of the encoder . |
| Outcome: | The proposed variant encourages the stochasticity of the encoder while achieving higher BLEU scores. |
Sequence-Level Mixed Sample Data Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. |
| Approach: | They propose a data augmentation approach to encourage compositional behavior in neural networks . they propose to softly combine input/output sequences from the training set . |
| Outcome: | The proposed approach yields 1.0 BLEU improvement on translation datasets over baselines. |
Rethinking Perturbations in Encoder-Decoders for Fast Training (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies have proposed various regularization methods to avoid over-fitting. |
| Approach: | They propose to use scheduled sampling and adversarial perturbations to regularize neural models but they are not efficient enough for training time. |
| Outcome: | The proposed methods achieve comparable scores even though they are faster. |