Papers with data augmentation policy

1 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations