Order-agnostic cross entropy for non-autoregressive machine translation
We propose a new training objective named orderagnostic cross entropy (OAXE) for fully nonautoregressive translation (NAT) models. OAXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a common source of the critical multimodality problem in NAT. Concret...
Saved in:
Main Authors: | DU, Cunxiao, TU, Zhaopeng, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6660 https://ink.library.smu.edu.sg/context/sis_research/article/7663/viewcontent/du21c.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
by: DU, Cunxiao, et al.
Published: (2022) -
Revisiting the Markov Property for machine translation
by: DU, Cunxiao, et al.
Published: (2024) -
MLCatchUp: Automated update of deprecated machine-learning APIs in Python
by: AGUS HARYONO, Stefanus, et al.
Published: (2021) -
TATL: Task Agnostic Transfer Learning for skin attributes detection
by: NGUYEN, Duy M.H., et al.
Published: (2022) -
Adaptive stabilization based on machine learning for column generation
by: SHEN, Yunzhuang, et al.
Published: (2024)