28 citations · 30 across the 2 of their papers we have counts for
2 papers
cs.CL2022★ 2 cited
Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
Lihua Qian, Mingxuan Wang, Yang Liu +1
Previously, non-autoregressive models were widely perceived as being superior in generation efficiency but inferior in generation quality due to the difficulties of modeling multip…
cs.CL2022★ 28 cited
Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Fei Huang, Hao Zhou, Yang Liu +2
Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel. However, such independent predictions prevent NATs from captu…