Iterative Translation-Based Data Augmentation Method for Text Classification Tasks

A well-known limitation of existing rule-based text augmentation is that it cannot be applied to other languages because it depends on grammatical and structural characteristics. Moreover, most text Generative Adversarial Networks (GAN) are unstable in training due to inefficient generator optimizat...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Sangwon Lee, Ling Liu, Wonik Choi
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2021-01-01
Edice:	IEEE Access
Témata:	Deep learning data augmentation natural language processing text classification
On-line přístup:	https://ieeexplore.ieee.org/document/9628110/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!