A Non-Autoregressive Neural Machine Translation Model With Iterative Length Update of Target Sentence

The non-autoregressive decoders in neural machine translation are paid increasing attention due to their faster decoding than autoregressive decoders. However, their apparent problem is a low performance which is mainly originated from wrong prediction about the target sentence length. To attack thi...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Main Authors: Yeon-Soo Lim, Eun-Ju Park, Hyun-Je Song, Seong-Bae Park
Formato: Artigo
Idioma:Inglês
Publicado em: IEEE 2022-01-01
Colecção:IEEE Access
Assuntos:
Machine translation
non-autoregressive decoder
sequence-to-sequence model
target length adaptation
transformer
Acesso em linha:https://ieeexplore.ieee.org/document/9761865/
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

Registos relacionados