@inproceedings{sarti-etal-2022-divemt,
title = "{D}iv{EMT}: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages",
author = "Sarti, Gabriele and
Bisazza, Arianna and
Guerberof-Arenas, Ana and
Toral, Antonio",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.532",
doi = "10.18653/v1/2022.emnlp-main.532",
pages = "7795--7816",
abstract = "We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sarti-etal-2022-divemt">
<titleInfo>
<title>DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Guerberof-Arenas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.</abstract>
<identifier type="citekey">sarti-etal-2022-divemt</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.532</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.532</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7795</start>
<end>7816</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
%A Sarti, Gabriele
%A Bisazza, Arianna
%A Guerberof-Arenas, Ana
%A Toral, Antonio
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F sarti-etal-2022-divemt
%X We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.
%R 10.18653/v1/2022.emnlp-main.532
%U https://aclanthology.org/2022.emnlp-main.532
%U https://doi.org/10.18653/v1/2022.emnlp-main.532
%P 7795-7816
Markdown (Informal)
[DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages](https://aclanthology.org/2022.emnlp-main.532) (Sarti et al., EMNLP 2022)
ACL