Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many case...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-08
Main Authors: Lee, Gyubok, Yang, Seongjun, Choi, Edward
Format: Article
Language:English
Subjects:
Component reliability
Machine translation
Terminology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Lee, Gyubok
Yang, Seongjun
Choi, Edward
description Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (>98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2526477418</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2526477418</sourcerecordid><originalsourceid>FETCH-proquest_journals_25264774183</originalsourceid><addsrcrecordid>eNqNTdsKgjAYHkGQlO8w6FrQebyXoiAjsHv5mStna7Ntdnj7JvQAXX185xnySBxHQZEQskC-MX0YhiTLSZrGHuL7-6DVk8srPrA3pyDEB5dKGquBS9biIxs1CFwB7RzHZw3SCLBcSfzitsO1GjVlgau0fFJdpQJzc1APIPFJs5bTyVih-QWEYf4Pl2i93ZzLXeD-HyMztundlHRWQ1KSJXmeREX8X-oLBEZI0w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2526477418</pqid></control><display><type>article</type><title>Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction</title><source>Publicly Available Content Database</source><creator>Lee, Gyubok ; Yang, Seongjun ; Choi, Edward</creator><creatorcontrib>Lee, Gyubok ; Yang, Seongjun ; Choi, Edward</creatorcontrib><description>Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (&gt;98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Component reliability ; Machine translation ; Terminology</subject><ispartof>arXiv.org, 2021-08</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2526477418?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25732,36991,44569</link.rule.ids></links><search><creatorcontrib>Lee, Gyubok</creatorcontrib><creatorcontrib>Yang, Seongjun</creatorcontrib><creatorcontrib>Choi, Edward</creatorcontrib><title>Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction</title><title>arXiv.org</title><description>Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (&gt;98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.</description><subject>Component reliability</subject><subject>Machine translation</subject><subject>Terminology</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNTdsKgjAYHkGQlO8w6FrQebyXoiAjsHv5mStna7Ntdnj7JvQAXX185xnySBxHQZEQskC-MX0YhiTLSZrGHuL7-6DVk8srPrA3pyDEB5dKGquBS9biIxs1CFwB7RzHZw3SCLBcSfzitsO1GjVlgau0fFJdpQJzc1APIPFJs5bTyVih-QWEYf4Pl2i93ZzLXeD-HyMztundlHRWQ1KSJXmeREX8X-oLBEZI0w</recordid><startdate>20210812</startdate><enddate>20210812</enddate><creator>Lee, Gyubok</creator><creator>Yang, Seongjun</creator><creator>Choi, Edward</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210812</creationdate><title>Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction</title><author>Lee, Gyubok ; Yang, Seongjun ; Choi, Edward</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25264774183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Component reliability</topic><topic>Machine translation</topic><topic>Terminology</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Gyubok</creatorcontrib><creatorcontrib>Yang, Seongjun</creatorcontrib><creatorcontrib>Choi, Edward</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lee, Gyubok</au><au>Yang, Seongjun</au><au>Choi, Edward</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction</atitle><jtitle>arXiv.org</jtitle><date>2021-08-12</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (&gt;98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2526477418
source Publicly Available Content Database
subjects Component reliability
Machine translation
Terminology
title Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T12%3A42%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Improving%20Lexically%20Constrained%20Neural%20Machine%20Translation%20with%20Source-Conditioned%20Masked%20Span%20Prediction&rft.jtitle=arXiv.org&rft.au=Lee,%20Gyubok&rft.date=2021-08-12&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2526477418%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_25264774183%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2526477418&rft_id=info:pmid/&rfr_iscdi=true