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,...

Full description

Saved in:
Bibliographic Details
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
id sg-smu-ink.sis_research-8619
record_format dspace
spelling sg-smu-ink.sis_research-86192022-12-22T03:24:55Z ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation DU, Cunxiao TU, Zhaopeng WANG, Longyue JIANG, Jing 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, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. Extensive experiments on NAT benchmarks across language pairs and data scales demonstrate the effectiveness and universality of our approach. Further analyses show that ngram noaxe indeed improves the translation of ngram phrases, and produces more fluent translation with a better modeling of sentence structure. 2022-10-01T07:00:00Z text application/pdf 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 http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
DU, Cunxiao
TU, Zhaopeng
WANG, Longyue
JIANG, Jing
ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
description 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, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. Extensive experiments on NAT benchmarks across language pairs and data scales demonstrate the effectiveness and universality of our approach. Further analyses show that ngram noaxe indeed improves the translation of ngram phrases, and produces more fluent translation with a better modeling of sentence structure.
format text
author DU, Cunxiao
TU, Zhaopeng
WANG, Longyue
JIANG, Jing
author_facet DU, Cunxiao
TU, Zhaopeng
WANG, Longyue
JIANG, Jing
author_sort DU, Cunxiao
title ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
title_short ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
title_full ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
title_fullStr ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
title_full_unstemmed ngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation
title_sort ngram-oaxe: phrase-based order-agnostic cross entropy for non-autoregressive machine translation
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url 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
_version_ 1770576395236278272