Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations

About

We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced with other words with paradigmatic relations. We stochastically replace words with other words that are predicted by a bi-directional language model at the word positions. Words predicted according to a context are numerous but appropriate for the augmentation of the original words. Furthermore, we retrofit a language model with a label-conditional architecture, which allows the model to augment sentences without breaking the label-compatibility. Through the experiments for six various different text classification tasks, we demonstrate that the proposed method improves classifiers based on the convolutional or recurrent neural networks.

Sosuke Kobayashi• 2018

Related benchmarks

TaskDatasetResultRank
Qualitative Evaluation of Generated SequencesAMAZON
Sentiment Preservation80
4
Qualitative Evaluation of Generated SequencesYelp
Sentiment Preservation82.9
4
Text ClassificationYelp Medium
F1 Score87
4
Text ClassificationAmazon Medium
F1 Score85
4
Text ClassificationAmazon Large
F1 Score92.9
4
Text ClassificationYelp-Large
F1 Score94
4
Showing 6 of 6 rows

Other info

Follow for update