A2R2: Robust Unsupervised Neural Machine Translation With Adversarial Attack and Regularization on Representations

Unsupervised neural machine translation (UNMT) has recently achieved significant progress without requirement on any parallel data. The models for UNMT are typically the sequence-to-sequence architecture with an encoder to map sentences in different languages to a shared latent space, and a decoder...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Heng Yu, Haoran Luo, Yuqi Yi, Fan Cheng
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	IEEE 2021-01-01
סדרה:	IEEE Access
נושאים:	Natural language processing machine translation unsupervised learning adversarial attack
גישה מקוונת:	https://ieeexplore.ieee.org/document/9336722/
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!