@inproceedings{qian-2023-performance,
title = "Performance Evaluation on Human-Machine Teaming Augmented Machine Translation Enabled by {GPT}-4",
author = "Qian, Ming",
editor = "Guti{\'e}rrez, Raquel L{\'a}zaro and
Pareja, Antonio and
Mitkov, Ruslan",
booktitle = "Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.nlp4tia-1.4",
pages = "20--31",
abstract = "Translation has been modeled as a multiple-phase process where pre-editing analyses guide meaning transfer and interlingual restructure. Present-day machine translation (MT) tools provide no means for source text analyses. Generative AI with Large language modeling (LLM), equipped with prompt engineering and fine-tuning capabilities, can enable augmented MT solutions by explicitly including AI or human generated analyses/instruction, and/or human-generated reference translation as pre-editing or interactive inputs. Using an English-to-Chinese translation piece that had been carefully studied during a translator slam event, Four types of translation outputs on 20 text segments were evaluated: human-generated translation, Google Translate MT, instruction-augmented MT using GPT4-LLM, and Human-Machine-Teaming (HMT)-augmented translation based on both human reference translation and instruction using GPT4-LLM. While human translation had the best performance, both augmented MT approaches performed better than un-augmented MT. The HMT-augmented MT performed better than instruction-augmented MT because it combined the guidance and knowledge provided by both human reference translation and style instruction. However, since it is unrealistic to generate sentence-by-sentence human translation as MT input, better approaches to HMT-augmented MT need to be invented. The evaluation showed that generative AI with LLM can enable new MT workflow facilitating pre-editing analyses and interactive restructuring and achieving better performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-2023-performance">
<titleInfo>
<title>Performance Evaluation on Human-Machine Teaming Augmented Machine Translation Enabled by GPT-4</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="given">Lázaro</namePart>
<namePart type="family">Gutiérrez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translation has been modeled as a multiple-phase process where pre-editing analyses guide meaning transfer and interlingual restructure. Present-day machine translation (MT) tools provide no means for source text analyses. Generative AI with Large language modeling (LLM), equipped with prompt engineering and fine-tuning capabilities, can enable augmented MT solutions by explicitly including AI or human generated analyses/instruction, and/or human-generated reference translation as pre-editing or interactive inputs. Using an English-to-Chinese translation piece that had been carefully studied during a translator slam event, Four types of translation outputs on 20 text segments were evaluated: human-generated translation, Google Translate MT, instruction-augmented MT using GPT4-LLM, and Human-Machine-Teaming (HMT)-augmented translation based on both human reference translation and instruction using GPT4-LLM. While human translation had the best performance, both augmented MT approaches performed better than un-augmented MT. The HMT-augmented MT performed better than instruction-augmented MT because it combined the guidance and knowledge provided by both human reference translation and style instruction. However, since it is unrealistic to generate sentence-by-sentence human translation as MT input, better approaches to HMT-augmented MT need to be invented. The evaluation showed that generative AI with LLM can enable new MT workflow facilitating pre-editing analyses and interactive restructuring and achieving better performance.</abstract>
<identifier type="citekey">qian-2023-performance</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4tia-1.4</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>20</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Performance Evaluation on Human-Machine Teaming Augmented Machine Translation Enabled by GPT-4
%A Qian, Ming
%Y Gutiérrez, Raquel Lázaro
%Y Pareja, Antonio
%Y Mitkov, Ruslan
%S Proceedings of the First Workshop on NLP Tools and Resources for Translation and Interpreting Applications
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F qian-2023-performance
%X Translation has been modeled as a multiple-phase process where pre-editing analyses guide meaning transfer and interlingual restructure. Present-day machine translation (MT) tools provide no means for source text analyses. Generative AI with Large language modeling (LLM), equipped with prompt engineering and fine-tuning capabilities, can enable augmented MT solutions by explicitly including AI or human generated analyses/instruction, and/or human-generated reference translation as pre-editing or interactive inputs. Using an English-to-Chinese translation piece that had been carefully studied during a translator slam event, Four types of translation outputs on 20 text segments were evaluated: human-generated translation, Google Translate MT, instruction-augmented MT using GPT4-LLM, and Human-Machine-Teaming (HMT)-augmented translation based on both human reference translation and instruction using GPT4-LLM. While human translation had the best performance, both augmented MT approaches performed better than un-augmented MT. The HMT-augmented MT performed better than instruction-augmented MT because it combined the guidance and knowledge provided by both human reference translation and style instruction. However, since it is unrealistic to generate sentence-by-sentence human translation as MT input, better approaches to HMT-augmented MT need to be invented. The evaluation showed that generative AI with LLM can enable new MT workflow facilitating pre-editing analyses and interactive restructuring and achieving better performance.
%U https://aclanthology.org/2023.nlp4tia-1.4
%P 20-31
Markdown (Informal)
[Performance Evaluation on Human-Machine Teaming Augmented Machine Translation Enabled by GPT-4](https://aclanthology.org/2023.nlp4tia-1.4) (Qian, NLP4TIA-WS 2023)
ACL