Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations
Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English-to-German: the better the given MT is, the harder...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
17.06.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English-to-German: the better the given MT is, the harder it is to decide what parts to edit and how to fix these errors. One possible solution to this problem is to instill deeper knowledge about the target language into the model. Thus, we propose a linguistically motivated method of regularization that is expected to enhance APE models' understanding of the target language: a loss function that encourages symmetric self-attention on the given MT. Our analysis of experimental results demonstrates that the proposed method helps improving the state-of-the-art architecture's APE quality for high-quality MTs. |
---|---|
AbstractList | Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English-to-German: the better the given MT is, the harder it is to decide what parts to edit and how to fix these errors. One possible solution to this problem is to instill deeper knowledge about the target language into the model. Thus, we propose a linguistically motivated method of regularization that is expected to enhance APE models' understanding of the target language: a loss function that encourages symmetric self-attention on the given MT. Our analysis of experimental results demonstrates that the proposed method helps improving the state-of-the-art architecture's APE quality for high-quality MTs. |
Author | Kim, Yunsu Jung, Baikjin Lee, Jong-Hyeok Lee, Myungji |
Author_xml | – sequence: 1 givenname: Baikjin surname: Jung fullname: Jung, Baikjin – sequence: 2 givenname: Myungji surname: Lee fullname: Lee, Myungji – sequence: 3 givenname: Jong-Hyeok surname: Lee fullname: Lee, Jong-Hyeok – sequence: 4 givenname: Yunsu surname: Kim fullname: Kim, Yunsu |
BookMark | eNqNjM0KwjAQhIMoWH_eYcFzoSa29lpF8SIo9l5CTWuk3dVke-jba8EH8DTDfDMzE2MkNCMRSKXWYbqRciqW3j-jKJLJVsaxCoTdOYs1nMkZyJgNsiUEJrj1yLpkW35d2xp2PVTkIOuYWj3EF_Js7paHOVVwsvUjvHa6sdzDWZcPiwZyp9E3evj0CzGpdOPN8qdzsToe8v0pfDl6d8Zz8aTO4RcVMl3HqUqSaKv-a30AW6JKXA |
ContentType | Paper |
Copyright | 2023. 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. |
Copyright_xml | – notice: 2023. 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. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection ProQuest Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28158366073 |
IEDL.DBID | 8FG |
IngestDate | Fri Sep 13 08:11:51 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28158366073 |
OpenAccessLink | https://www.proquest.com/docview/2815836607/abstract/?pq-origsite=%requestingapplication% |
PQID | 2815836607 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2815836607 |
PublicationCentury | 2000 |
PublicationDate | 20230617 |
PublicationDateYYYYMMDD | 2023-06-17 |
PublicationDate_xml | – month: 06 year: 2023 text: 20230617 day: 17 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.4646425 |
SecondaryResourceType | preprint |
Snippet | Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Machine translation Regularization Symmetry |
Title | Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations |
URI | https://www.proquest.com/docview/2815836607/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfZ07a8MwEMePNKbQrU_6SIOgXU0iK35kKkmxawoJpg_IFiRZhgyxU0cZvPSzV6ck7VDIJiMwthB3p79-dwfwaIy-iChVruCoVpkDhMsLJt2cRkUx5KHKcwvIToP0c_A682ctSPe5MIhV7m2iNdR5JVEj73kR9SMWBP2wxwWqAFL3nlZfLvaPwnvWXTONI3Ao1sTDnPHk5Vdt8YLQxM7sn8G1XiQ5BSfjK1WfQUuV53Bs4Uu5voDFGMU1MqlqRUZabwFEoivy3pTaJjGZ0XKpdN0QE2OS0UZXttIqyWyKxgLRZVIVBKENd1sVoyETi0kqYr3Rjni7hIck_nhO3f33zXd7aT3_-3N2Be2yKtU1kCIQQb9QUpiQYsAFFbk5R_hMedJjXA3ZDXQOven28PQdnGBbdUSiaNiBtq436t44Xy26dl274IzjafZmnibf8Q90G5JD |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfZ3PS8MwFMcfuiF68yf-mBrQa3Fp2rQ7yRRr1XUMnLBbadoEdlgz2-zQ_94k6_Qg7BYIhCSE916--bw8gHtt9FmIMXdYZtQqfYFwMkFyp8ChEIMs4EVhAdkxjb-895k_awW3usUqNzbRGupC5kYjf3BD7IeE0n7wuPx2TNUo87raltDYha5HtOs0meLR66_G4tJAR8zkn5m1viM6hO4kW_LqCHZ4eQx7FrnM6xOYPxlJDSWy4mio1Bo7REqiz6ZUNnVJtxYLrqoG6cgSDVdK2v9V0cQmZswNsIykQAbVcNZ_YTQosXAkR9YHtZzbKdxFL9Pn2NnML21PUJ3-rZecQaeUJT8HJCijfcFzpgMJL2OYFfr24BPu5i7J-IBcQG_bSJfbu29hP54mo3T0Nv64ggNTWN1AUTjoQUdVK36t3a9iN3aPfwCLwo6m |
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=article&rft.atitle=Bring+More+Attention+to+Syntactic+Symmetry+for+Automatic+Postediting+of+High-Quality+Machine+Translations&rft.jtitle=arXiv.org&rft.au=Jung%2C+Baikjin&rft.au=Lee%2C+Myungji&rft.au=Lee%2C+Jong-Hyeok&rft.au=Kim%2C+Yunsu&rft.date=2023-06-17&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |