Papers with sequence-to-sequence problems
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. |