AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation

Xiangyu Qu; Guojing Liu; Liang Li

2025 ICML ICML 2025

AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Xiangyu Qu, Guojing Liu, Liang Li

Topics

Natural Language Processing > Applications > Machine Translation

Keywords

inference efficiency non-autoregressive transformer target information training-inference gap quantization alignment training framework semantic consistency space

Download PDF