@inproceedings{vidal-etal-2022-automatic,
title = "Automatic Post-Editing of {MT} Output Using Large Language Models",
author = "Vidal, Blanca and
Llorens, Albert and
Alonso, Juan",
editor = "Campbell, Janice and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)",
month = sep,
year = "2022",
address = "Orlando, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-upg.7",
pages = "84--106",
abstract = "This presentation will show two experiments conducted to evaluate the adequacy of OpenAI{'}s GPT-3 (as a representative of Large Language Models), for the purposes of post-editing and translating texts from English into Spanish, using a glossary of terms to ensure term consistency. The experiments are motivated by a use case in ULG MT Production, where we need to improve the usage of terminology glossaries in our NMT system. The purpose of the experiments is to take advantage of GPT-3 outstanding capabilities to generate text for completion and editing. We have used the edits end-point to post-edit the output of a NMT system using a glossary, and the completions end-point to translate the source text, including the glossary term list in the corresponding GPT-3 prompt. While the results are promising, they also show that there is room for improvement by fine-tuning the models, working on prompt engineering, and adjusting the requests parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vidal-etal-2022-automatic">
<titleInfo>
<title>Automatic Post-Editing of MT Output Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Blanca</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Llorens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Alonso</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 (Volume 2: Users and Providers Track and Government Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Orlando, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This presentation will show two experiments conducted to evaluate the adequacy of OpenAI’s GPT-3 (as a representative of Large Language Models), for the purposes of post-editing and translating texts from English into Spanish, using a glossary of terms to ensure term consistency. The experiments are motivated by a use case in ULG MT Production, where we need to improve the usage of terminology glossaries in our NMT system. The purpose of the experiments is to take advantage of GPT-3 outstanding capabilities to generate text for completion and editing. We have used the edits end-point to post-edit the output of a NMT system using a glossary, and the completions end-point to translate the source text, including the glossary term list in the corresponding GPT-3 prompt. While the results are promising, they also show that there is room for improvement by fine-tuning the models, working on prompt engineering, and adjusting the requests parameters.</abstract>
<identifier type="citekey">vidal-etal-2022-automatic</identifier>
<location>
<url>https://aclanthology.org/2022.amta-upg.7</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>84</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Post-Editing of MT Output Using Large Language Models
%A Vidal, Blanca
%A Llorens, Albert
%A Alonso, Juan
%Y Campbell, Janice
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F vidal-etal-2022-automatic
%X This presentation will show two experiments conducted to evaluate the adequacy of OpenAI’s GPT-3 (as a representative of Large Language Models), for the purposes of post-editing and translating texts from English into Spanish, using a glossary of terms to ensure term consistency. The experiments are motivated by a use case in ULG MT Production, where we need to improve the usage of terminology glossaries in our NMT system. The purpose of the experiments is to take advantage of GPT-3 outstanding capabilities to generate text for completion and editing. We have used the edits end-point to post-edit the output of a NMT system using a glossary, and the completions end-point to translate the source text, including the glossary term list in the corresponding GPT-3 prompt. While the results are promising, they also show that there is room for improvement by fine-tuning the models, working on prompt engineering, and adjusting the requests parameters.
%U https://aclanthology.org/2022.amta-upg.7
%P 84-106
Markdown (Informal)
[Automatic Post-Editing of MT Output Using Large Language Models](https://aclanthology.org/2022.amta-upg.7) (Vidal et al., AMTA 2022)
ACL
- Blanca Vidal, Albert Llorens, and Juan Alonso. 2022. Automatic Post-Editing of MT Output Using Large Language Models. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track), pages 84–106, Orlando, USA. Association for Machine Translation in the Americas.