ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss. Starting from the intuition that reordering generally occurs between phrases,...
Saved in:
Main Authors: | DU, Cunxiao, TU, Zhaopeng, WANG, Longyue, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7616 https://ink.library.smu.edu.sg/context/sis_research/article/8619/viewcontent/2022.coling_1.446.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Order-agnostic cross entropy for non-autoregressive machine translation
by: DU, Cunxiao, et al.
Published: (2021) -
Revisiting the Markov Property for machine translation
by: DU, Cunxiao, et al.
Published: (2024) -
Topological ordering of function words in hierarchical phrase-based translation
by: Setiawan, H., et al.
Published: (2013) -
Efficient and effective KNN sequence search with approximate ngrams
by: Wang, X., et al.
Published: (2014) -
Phrase-based statistical machine translation: A level of detail approach
by: Setiawan, H., et al.
Published: (2013)