Structure-Invariant Testing for Machine Translation

In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various applications, such as describing symptoms to a foreign doctor and reading political news in a foreign language. However, the complexity and intrac...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE) s. 961 - 973
Hlavní autoři: He, Pinjia, Meister, Clara, Su, Zhendong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.10.2020
Témata:
ISSN:1558-1225
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various applications, such as describing symptoms to a foreign doctor and reading political news in a foreign language. However, the complexity and intractability of neural machine translation (NMT) models that power modern machine translation make the robustness of these systems difficult to even assess, much less guarantee. Machine translation systems can return inferior results that lead to misunderstanding, medical misdiagnoses, threats to personal safety, or political conflicts. Despite its apparent importance, validating the robustness of machine translation systems is very difficult and has, therefore, been much under-explored. To tackle this challenge, we introduce structure-invariant testing (SIT), a novel metamorphic testing approach for validating machine translation software. Our key insight is that the translation results of "similar" source sentences should typically exhibit similar sentence structures. Specifically, SIT (1) generates similar source sentences by substituting one word in a given sentence with semantically similar, syntactically equivalent words; (2) represents sentence structure by syntax parse trees (obtained via constituency or dependency parsing); (3) reports sentence pairs whose structures differ quantitatively by more than some threshold. To evaluate SIT, we use it to test Google Translate and Bing Microsoft Translator with 200 source sentences as input, which led to 64 and 70 buggy issues with 69.5% and 70% top-1 accuracy, respectively. The translation errors are diverse, including under-translation, over-translation, incorrect modification, word/phrase mistranslation, and unclear logic.
AbstractList In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various applications, such as describing symptoms to a foreign doctor and reading political news in a foreign language. However, the complexity and intractability of neural machine translation (NMT) models that power modern machine translation make the robustness of these systems difficult to even assess, much less guarantee. Machine translation systems can return inferior results that lead to misunderstanding, medical misdiagnoses, threats to personal safety, or political conflicts. Despite its apparent importance, validating the robustness of machine translation systems is very difficult and has, therefore, been much under-explored. To tackle this challenge, we introduce structure-invariant testing (SIT), a novel metamorphic testing approach for validating machine translation software. Our key insight is that the translation results of "similar" source sentences should typically exhibit similar sentence structures. Specifically, SIT (1) generates similar source sentences by substituting one word in a given sentence with semantically similar, syntactically equivalent words; (2) represents sentence structure by syntax parse trees (obtained via constituency or dependency parsing); (3) reports sentence pairs whose structures differ quantitatively by more than some threshold. To evaluate SIT, we use it to test Google Translate and Bing Microsoft Translator with 200 source sentences as input, which led to 64 and 70 buggy issues with 69.5% and 70% top-1 accuracy, respectively. The translation errors are diverse, including under-translation, over-translation, incorrect modification, word/phrase mistranslation, and unclear logic.
Author Su, Zhendong
Meister, Clara
He, Pinjia
Author_xml – sequence: 1
  givenname: Pinjia
  surname: He
  fullname: He, Pinjia
  email: pinjia.he@inf.ethz.ch
  organization: ETH Zurich,Department of Computer Science,Switzerland
– sequence: 2
  givenname: Clara
  surname: Meister
  fullname: Meister, Clara
  email: clara.meister@inf.ethz.ch
  organization: ETH Zurich,Department of Computer Science,Switzerland
– sequence: 3
  givenname: Zhendong
  surname: Su
  fullname: Su, Zhendong
  email: zhendong.su@inf.ethz.ch
  organization: ETH Zurich,Department of Computer Science,Switzerland
BookMark eNotzD1PwzAQgGGDQKIpzAws-QMpPl9c2yOq-KhUxECYq8v1AkbFQY6LxL8HCaZXeoa3UidpTKLUJegFQGuvEZ3zAAtErxHDkap-VaMDA3isZmCtb8AYe6aqaXrXWi_bEGYKn0s-cDlkadbpi3KkVOpOphLTaz2MuX4kfotJ6i5TmvZU4pjO1elA-0ku_jtXL3e33eqh2Tzdr1c3m4ZM60pjCYIE551lY7XeYc8GAge_454do7E0MDL3IoDYWu9bohC82OVgWA84V1d_3ygi288cPyh_b4PxrdYGfwA3fkWs
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1145/3377811.3380339
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore: IEL
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 1450371213
9781450371216
EISSN 1558-1225
EndPage 973
ExternalDocumentID 9284002
Genre orig-research
GroupedDBID -~X
.4S
.DC
123
23M
29O
5VS
6IE
6IF
6IH
6IK
6IL
6IM
6IN
8US
AAJGR
AAWTH
ABLEC
ADZIZ
AFFNX
ALMA_UNASSIGNED_HOLDINGS
APO
ARCSS
AVWKF
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
EDO
FEDTE
I-F
I07
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
XOL
ID FETCH-LOGICAL-a247t-5a19e97875c2500d3bc219c98dcbc7c325afc3ccbee13345884aa998e56f2c0f3
IEDL.DBID RIE
ISICitedReferencesCount 69
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000652529800079&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:32:58 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a247t-5a19e97875c2500d3bc219c98dcbc7c325afc3ccbee13345884aa998e56f2c0f3
PageCount 13
ParticipantIDs ieee_primary_9284002
PublicationCentury 2000
PublicationDate 2020-Oct.
PublicationDateYYYYMMDD 2020-10-01
PublicationDate_xml – month: 10
  year: 2020
  text: 2020-Oct.
PublicationDecade 2020
PublicationTitle 2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE)
PublicationTitleAbbrev ICSE
PublicationYear 2020
Publisher ACM
Publisher_xml – name: ACM
SSID ssj0006499
ssj0002870079
Score 2.4986947
Snippet In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various...
SourceID ieee
SourceType Publisher
StartPage 961
SubjectTerms Machine translation
Metamorphic testing
Structural invariance
Title Structure-Invariant Testing for Machine Translation
URI https://ieeexplore.ieee.org/document/9284002
WOSCitedRecordID wos000652529800079&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVKxcBUoEV8ywMjbhOfE8czooKBqhJF6lY5lytiSVFp-_t7dkMREgtLZGXyh3x3z3fvnRB3ZW4K0miUcRV_OGBVzmdOJQCuSj2hJozNJuxoVEynbtwS93suDBHF4jPqh2HM5VcLXIensoFjWxqVIw-szXdcrf17SkjYJSHj1FjhnEP5RsonNdkAwAZOZZ8RWZjGr14q0ZUMO_-bxLHo_XDy5HjvbU5Ei-pT0fluyiCbO9oV8BoVYddLUs_1hpEwb52cBC2N-l1yhCpfYvkkyeildpVwPfE2fJw8PKmmM4Ly2tiVynzqiPGfzZBDmKSCEtnyoCsqLNEi6MzPERBLIsagkYzqPQMryvK5xmQOZ6JdL2o6F9J6QGN1GTIuxqdQFoBgEnJQYOmNvRDdsAezz534xaxZ_uXfv6_EkQ6ANFa7XYs2r5huxCFuVh9fy9t4Ylvl-JWE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEJ0QNNETKhi_7cGjhd22S7dnI4EIhERMuJF2djBeVoPA77ctK8bEi5dNs6d-pDPzOjPvAdy5rspJoOLKFP7jA1ZubGZ4IqUpUksoCKPYhB6P89nMTGpwv-uFIaJYfEbtMIy5_OId1-GprGO8LY3MkXtBOavq1tq9qISUXRJyTpUd7vpgviLzSVXWkVKHrsq2x2RhIr_UVKIz6TX-N40jaP105bHJzt8cQ43KE2h8yzKw6pY2QT5HTtj1kvig3Hgs7DePTQObRvnKfIzKRrGAklj0U9tauBa89B6nD31eaSNwK5Re8cymhjwC1Bn6ICYppENve9DkBTrUKEVmFygRHZFHobEd1VoPrSjrLgQmC3kK9fK9pDNg2kpUWriQc1E2lS6XKFVCRuborNLn0Ax7MP_Y0l_Mq-Vf_P37Fg7609FwPhyMny7hUAR4GmvfrqDuV0_XsI-b1dvn8iae3hfkD5jN
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=2020+IEEE%2FACM+42nd+International+Conference+on+Software+Engineering+%28ICSE%29&rft.atitle=Structure-Invariant+Testing+for+Machine+Translation&rft.au=He%2C+Pinjia&rft.au=Meister%2C+Clara&rft.au=Su%2C+Zhendong&rft.date=2020-10-01&rft.pub=ACM&rft.eissn=1558-1225&rft.spage=961&rft.epage=973&rft_id=info:doi/10.1145%2F3377811.3380339&rft.externalDocID=9284002