@inproceedings{yuksel-etal-2022-efficient,
title = "Efficient Machine Translation Corpus Generation",
author = "Yuksel, Kamer Ali and
Gunduz, Ahmet and
Sharma, Shreyas and
Sawaf, Hassan",
editor = "Ortega, John E. and
Carpuat, Marine and
Chen, William and
Kann, Katharina and
Lignos, Constantine and
Popovic, Maja and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation)",
month = sep,
year = "2022",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-coco4mt.2",
pages = "11--17",
abstract = "This paper proposes an efficient and semi-automated method for human-in-the-loop post- editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypothe- ses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check mechanism for post-edits and remove the need for ad- ditional linguists to review them or work on the same hypotheses. In this paper, the effect of prioritizing with the proposed method on the resulting MT corpus quality is presented versus scheduling hypotheses randomly. As demonstrated by experiments, the proposed method im- proves the lifecycle of MT models by focusing the linguist effort on production samples and hypotheses, which matter most for expanding MT corpora to be used for re-training them",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuksel-etal-2022-efficient">
<titleInfo>
<title>Efficient Machine Translation Corpus Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamer</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Yuksel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Gunduz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreyas</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation)</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes an efficient and semi-automated method for human-in-the-loop post- editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypothe- ses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check mechanism for post-edits and remove the need for ad- ditional linguists to review them or work on the same hypotheses. In this paper, the effect of prioritizing with the proposed method on the resulting MT corpus quality is presented versus scheduling hypotheses randomly. As demonstrated by experiments, the proposed method im- proves the lifecycle of MT models by focusing the linguist effort on production samples and hypotheses, which matter most for expanding MT corpora to be used for re-training them</abstract>
<identifier type="citekey">yuksel-etal-2022-efficient</identifier>
<location>
<url>https://aclanthology.org/2022.amta-coco4mt.2</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>11</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Machine Translation Corpus Generation
%A Yuksel, Kamer Ali
%A Gunduz, Ahmet
%A Sharma, Shreyas
%A Sawaf, Hassan
%Y Ortega, John E.
%Y Carpuat, Marine
%Y Chen, William
%Y Kann, Katharina
%Y Lignos, Constantine
%Y Popovic, Maja
%Y Tafreshi, Shabnam
%S Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%F yuksel-etal-2022-efficient
%X This paper proposes an efficient and semi-automated method for human-in-the-loop post- editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypothe- ses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check mechanism for post-edits and remove the need for ad- ditional linguists to review them or work on the same hypotheses. In this paper, the effect of prioritizing with the proposed method on the resulting MT corpus quality is presented versus scheduling hypotheses randomly. As demonstrated by experiments, the proposed method im- proves the lifecycle of MT models by focusing the linguist effort on production samples and hypotheses, which matter most for expanding MT corpora to be used for re-training them
%U https://aclanthology.org/2022.amta-coco4mt.2
%P 11-17
Markdown (Informal)
[Efficient Machine Translation Corpus Generation](https://aclanthology.org/2022.amta-coco4mt.2) (Yuksel et al., AMTA 2022)
ACL
- Kamer Ali Yuksel, Ahmet Gunduz, Shreyas Sharma, and Hassan Sawaf. 2022. Efficient Machine Translation Corpus Generation. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation), pages 11–17, None. Association for Machine Translation in the Americas.