Generating Diverse Translation by Manipulating Multi-Head Attention
원문 초록
Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. We empirically verify this discovery and propose a method to generate diverse translations by manipulating heads. Furthermore, we make use of these diverse translations with the back-translation technique for better data augmentation. Experiment results show that our method generates diverse translations without severe drop in translation quality. Experiments also show that back-translation with these diverse translations could bring significant improvement on performance on translation tasks. An auxiliary experiment of conversation response generation task proves the effect of diversity as well.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse Regression Codes exploit Multi-User Diversity without CSI
orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
DGSSC: A Deep Generative Spectral-Spatial Classifier for Imbalanced Hyperspectral Imagery
Effective Deep Learning Models for Automatic Diacritization of Arabic Text
토론
이 논문과 연결된 포럼 글이 아직 없습니다.