Creative and Context-Aware Translation of East Asian Idioms with GPT-4

As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tang, Kenan, Song, Peiyang, Qin, Yao, Yan, Xifeng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Tang, Kenan
Song, Peiyang
Qin, Yao
Yan, Xifeng
description As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of candidate translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more high-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.
doi_str_mv 10.48550/arxiv.2410.00988
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2410_00988</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2410_00988</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2410_009883</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgEKGBhYWlhwMrg5F6UmlmSWpSok5qUoOOfnlaRWlOg6licWpSqEFCXmFecAZfPzFPLTFFwTi0sUHIszE_MUPFMy83OLFcozSzIU3ANCdE14GFjTEnOKU3mhNDeDvJtriLOHLtjG-IKizNzEosp4kM3xYJuNCasAAPJRN6w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Creative and Context-Aware Translation of East Asian Idioms with GPT-4</title><source>arXiv.org</source><creator>Tang, Kenan ; Song, Peiyang ; Qin, Yao ; Yan, Xifeng</creator><creatorcontrib>Tang, Kenan ; Song, Peiyang ; Qin, Yao ; Yan, Xifeng</creatorcontrib><description>As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of candidate translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more high-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.</description><identifier>DOI: 10.48550/arxiv.2410.00988</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2024-10</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2410.00988$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2410.00988$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Tang, Kenan</creatorcontrib><creatorcontrib>Song, Peiyang</creatorcontrib><creatorcontrib>Qin, Yao</creatorcontrib><creatorcontrib>Yan, Xifeng</creatorcontrib><title>Creative and Context-Aware Translation of East Asian Idioms with GPT-4</title><description>As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of candidate translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more high-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMgEKGBhYWlhwMrg5F6UmlmSWpSok5qUoOOfnlaRWlOg6licWpSqEFCXmFecAZfPzFPLTFFwTi0sUHIszE_MUPFMy83OLFcozSzIU3ANCdE14GFjTEnOKU3mhNDeDvJtriLOHLtjG-IKizNzEosp4kM3xYJuNCasAAPJRN6w</recordid><startdate>20241001</startdate><enddate>20241001</enddate><creator>Tang, Kenan</creator><creator>Song, Peiyang</creator><creator>Qin, Yao</creator><creator>Yan, Xifeng</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241001</creationdate><title>Creative and Context-Aware Translation of East Asian Idioms with GPT-4</title><author>Tang, Kenan ; Song, Peiyang ; Qin, Yao ; Yan, Xifeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2410_009883</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Tang, Kenan</creatorcontrib><creatorcontrib>Song, Peiyang</creatorcontrib><creatorcontrib>Qin, Yao</creatorcontrib><creatorcontrib>Yan, Xifeng</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tang, Kenan</au><au>Song, Peiyang</au><au>Qin, Yao</au><au>Yan, Xifeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Creative and Context-Aware Translation of East Asian Idioms with GPT-4</atitle><date>2024-10-01</date><risdate>2024</risdate><abstract>As a type of figurative language, an East Asian idiom condenses rich cultural background into only a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of candidate translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more high-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.</abstract><doi>10.48550/arxiv.2410.00988</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2410.00988
ispartof
issn
language eng
recordid cdi_arxiv_primary_2410_00988
source arXiv.org
subjects Computer Science - Computation and Language
title Creative and Context-Aware Translation of East Asian Idioms with GPT-4
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T13%3A52%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Creative%20and%20Context-Aware%20Translation%20of%20East%20Asian%20Idioms%20with%20GPT-4&rft.au=Tang,%20Kenan&rft.date=2024-10-01&rft_id=info:doi/10.48550/arxiv.2410.00988&rft_dat=%3Carxiv_GOX%3E2410_00988%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true