TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models

TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models Bouthaina Abdou, Hossam Elsafty, Farizeh Aldabbas, Maren Pielka, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8007453/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 16 You are reading this latest preprint version Abstract Arabic, one of the world’s most widely spoken languages, is marked by extensive dialectal variation that often differs significantly from Modern Standard Arabic (MSA) and from other dialects. This linguistic diversity presents considerable challenges for machine translation systems, especially when translating dialectal Arabic into MSA or English. Addressing this gap, this work introduces TARGAMA, a novel benchmark dataset and framework designed to improve dialectal Arabic-English translation by leveraging state-of-the-art generative language models. As part of this work, we develop the largest known multi-dialectal Arabic-English parallel corpus, covering six major dialects. Using this dataset, we evaluate a variety of generative language models and propose a unified framework for dialect-aware translation. Our approach demonstrates strong performance across dialects and offers a scalable solution for improving translation quality in low-resource and linguistically diverse settings. Dialectal Arabic Machine Translation Benchmark Generative Language Models Full Text Additional Declarations No competing interests reported. Supplementary Files samples2.zip Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 12 Dec, 2025 Reviews received at journal 12 Dec, 2025 Reviews received at journal 09 Dec, 2025 Reviews received at journal 08 Dec, 2025 Reviews received at journal 26 Nov, 2025 Reviews received at journal 15 Nov, 2025 Reviewers agreed at journal 13 Nov, 2025 Reviewers agreed at journal 12 Nov, 2025 Reviewers agreed at journal 12 Nov, 2025 Reviewers agreed at journal 11 Nov, 2025 Reviewers agreed at journal 11 Nov, 2025 Reviewers agreed at journal 10 Nov, 2025 Reviewers invited by journal 10 Nov, 2025 Editor assigned by journal 10 Nov, 2025 Submission checks completed at journal 07 Nov, 2025 First submitted to journal 01 Nov, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8007453","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":545428876,"identity":"b2d58a00-f119-4278-bc4b-5bcd431261d8","order_by":0,"name":"Bouthaina Abdou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYBACAyBmZmCQALHZGHgYGORArAMP8GthbEbWYgzWkkBYCwNcS2IDiIlPizl7j/njghqLPP7+w88evKk4nD4/7PBDoC12croN2LVY9pwxbJ5xTKJY4kaaueGcM4dzN95OMwBqSTY2O4DDYTdyDJt52CQSG24wmEnztgG1zE4AaTmQuA2vln8SifPPH/8G0pJuODv9A2EtvG0SiRsO5IBtSZCXzsFvi2XPscLZvH0SiRtv5JQD/ZJuuEE6p+BAggFuv5izN2/4zPOtLnHe+ePbgCFmLS8/O33zhw8VdnK4tGBxKlilAbHKQUC+gRTVo2AUjIJRMBIAAEpQZUYv+o6JAAAAAElFTkSuQmCC","orcid":"","institution":"University of Bonn","correspondingAuthor":true,"prefix":"","firstName":"Bouthaina","middleName":"","lastName":"Abdou","suffix":""},{"id":545428877,"identity":"d013f9d5-e3bc-4a11-933c-cc83dfe4e0f8","order_by":1,"name":"Hossam Elsafty","email":"","orcid":"","institution":"Fraunhofer Institute for Intelligent Analysis and Information Systems","correspondingAuthor":false,"prefix":"","firstName":"Hossam","middleName":"","lastName":"Elsafty","suffix":""},{"id":545428878,"identity":"89829228-7da1-440e-b5a0-afe63a9abb30","order_by":2,"name":"Farizeh Aldabbas","email":"","orcid":"","institution":"Fraunhofer Institute for Intelligent Analysis and Information Systems","correspondingAuthor":false,"prefix":"","firstName":"Farizeh","middleName":"","lastName":"Aldabbas","suffix":""},{"id":545428881,"identity":"2b1179fb-2840-4b6a-8584-f37d390ccea5","order_by":3,"name":"Maren Pielka","email":"","orcid":"","institution":"Fraunhofer Institute for Intelligent Analysis and Information Systems","correspondingAuthor":false,"prefix":"","firstName":"Maren","middleName":"","lastName":"Pielka","suffix":""},{"id":545428887,"identity":"df8a4fdd-dcbb-43fb-beab-52e3ea47bb93","order_by":4,"name":"Rafet Sifa","email":"","orcid":"","institution":"Fraunhofer Institute for Intelligent Analysis and Information Systems","correspondingAuthor":false,"prefix":"","firstName":"Rafet","middleName":"","lastName":"Sifa","suffix":""},{"id":545428888,"identity":"7426d3fd-5a0d-4c79-8ec7-3c954f0503c3","order_by":5,"name":"Lucie Flek","email":"","orcid":"","institution":"University of Bonn","correspondingAuthor":false,"prefix":"","firstName":"Lucie","middleName":"","lastName":"Flek","suffix":""}],"badges":[],"createdAt":"2025-11-01 18:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8007453/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8007453/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96341288,"identity":"7a0cf035-95c0-44f5-b9eb-3db4ecc7a53c","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7086,"visible":true,"origin":"","legend":"","description":"","filename":"10abf680cfec4f8e9030edc565b11917.json","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7ed7510dbd044340820905c2.json"},{"id":96341284,"identity":"647afd78-f6a1-4eda-8602-273c953ddf42","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1489688,"visible":true,"origin":"","legend":"","description":"","filename":"1000115689.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/131c00c5fa71fba89fa511bc.png"},{"id":96341297,"identity":"3af57a88-4c1b-4958-92d1-23591118e88d","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1177931,"visible":true,"origin":"","legend":"","description":"","filename":"AFrameworkforTranslatingDialectalArabicwithGenerativeLanguageModels11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/699a05c131e8f8339f022119.pdf"},{"id":96367038,"identity":"34575042-f935-4710-b933-220c5be2ccf1","added_by":"auto","created_at":"2025-11-20 10:12:07","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90484,"visible":true,"origin":"","legend":"","description":"","filename":"CoverLetter3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/9d7b0cf66404e9348f8147d5.pdf"},{"id":96341289,"identity":"f014260e-b4c8-4993-9c74-d3c8bd3f7dbb","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25624,"visible":true,"origin":"","legend":"","description":"","filename":"Finetunedmethod.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/0c43c2a2770e1c00f68fd419.pdf"},{"id":96367338,"identity":"95a64c3f-0ac5-4118-ad70-455202fe3650","added_by":"auto","created_at":"2025-11-20 10:12:35","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":285850,"visible":true,"origin":"","legend":"","description":"","filename":"Iraqi.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c0452f8e8e77683765f33fc3.png"},{"id":96341286,"identity":"4fabaaef-6543-4b1a-bdd2-d13e8bff8959","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70877,"visible":true,"origin":"","legend":"","description":"","filename":"Screenshot20251101at18.01.57.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/f130a68390dcdab6ccd36594.png"},{"id":96367596,"identity":"d62d65a1-33d2-4447-8edc-d8bb663f871c","added_by":"auto","created_at":"2025-11-20 10:13:28","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":204862,"visible":true,"origin":"","legend":"","description":"","filename":"TARGAMADiagramm1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/058e537764b1f35cd1d83f28.png"},{"id":96341296,"identity":"f765ae43-5303-45b8-886a-9375b56e8713","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2328059,"visible":true,"origin":"","legend":"","description":"","filename":"TARGAMAmodified.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c55905762aa57c998171b130.png"},{"id":96366931,"identity":"8b62fef7-3323-452f-a365-6bad806bb9b5","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2324789,"visible":true,"origin":"","legend":"","description":"","filename":"TargamaDiagrammodified1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/8ab71313cb07d26fd0914f52.png"},{"id":96365869,"identity":"3f0a9161-b339-493e-80d3-8e194e73c749","added_by":"auto","created_at":"2025-11-20 10:10:53","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2325746,"visible":true,"origin":"","legend":"","description":"","filename":"TargamaDiagrammodified.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/d5e2826cb22e48e66efebae7.png"},{"id":96341301,"identity":"f368a999-c0fe-4484-b983-5b52158072af","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":284560,"visible":true,"origin":"","legend":"","description":"","filename":"Yemeni.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/27678d5620fb7847ff139578.png"},{"id":96366532,"identity":"76160488-ecee-4bfa-bf3a-4068ee33331b","added_by":"auto","created_at":"2025-11-20 10:11:32","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93370,"visible":true,"origin":"","legend":"","description":"","filename":"YouTubedata1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/ca9b6998cb0a5363d07374eb.png"},{"id":96341298,"identity":"41678787-1026-4914-a31f-d52260a0b5d2","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":295608,"visible":true,"origin":"","legend":"","description":"","filename":"all.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/9a69b720ec7fc0f57c4458bc.png"},{"id":96365752,"identity":"adf718db-730b-4a97-a555-5a73f1af8f58","added_by":"auto","created_at":"2025-11-20 10:10:44","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":304248,"visible":true,"origin":"","legend":"","description":"","filename":"darija.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/50b7f02fa6bbf083ec94f2f0.png"},{"id":96366872,"identity":"ee386ed4-4ae3-457f-9e20-909750b5245b","added_by":"auto","created_at":"2025-11-20 10:11:59","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":479091,"visible":true,"origin":"","legend":"","description":"","filename":"darijawc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c43f70d5fb428cf4f3e2d050.png"},{"id":96341318,"identity":"ebc1776d-f00a-4679-9933-21f773b80c35","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54126,"visible":true,"origin":"","legend":"","description":"","filename":"distr.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/5e5980005f48379e47cd2ecb.png"},{"id":96341312,"identity":"24aa9379-2875-4b94-80ca-376cf70b7dab","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"pdf","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41824,"visible":true,"origin":"","legend":"","description":"","filename":"draftthesis1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/e0ada1f12cb630a277a42060.pdf"},{"id":96341306,"identity":"c2a91107-0f9c-467d-a61c-21de042fda50","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"pdf","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45179,"visible":true,"origin":"","legend":"","description":"","filename":"draftthesis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/303faf8458cb9d25db20073b.pdf"},{"id":96341317,"identity":"f01b0281-cb9b-4c26-bd94-b694106909b4","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":445564,"visible":true,"origin":"","legend":"","description":"","filename":"egwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/ebbf860c4d6303a46a77899d.png"},{"id":96366929,"identity":"0b7a8866-d091-4b56-aa95-99338c7ea222","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":302758,"visible":true,"origin":"","legend":"","description":"","filename":"egy.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/62da9eb30d3f7cfbdc14067f.png"},{"id":96341291,"identity":"01c8db26-7389-4e46-bef0-d91f706c0a83","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"eps","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/d5ec0d6262bf8755fa18149c.eps"},{"id":96366909,"identity":"ec15744c-c5f3-4f05-8911-f2f942a40435","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"eps","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c1fbe137bba56220d3174bac.eps"},{"id":96366984,"identity":"d22d72e2-d526-4d21-8c2b-0b27ad116fec","added_by":"auto","created_at":"2025-11-20 10:12:04","extension":"pdf","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25539,"visible":true,"origin":"","legend":"","description":"","filename":"finetunestrat.drawio.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/513c260a8a5b905ce7622ad2.pdf"},{"id":96367161,"identity":"2ce733db-84bc-4fc5-a8cd-0c32231764e9","added_by":"auto","created_at":"2025-11-20 10:12:14","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":294139,"visible":true,"origin":"","legend":"","description":"","filename":"gulf.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/9ecfd9ade36cb9758b3d4d59.png"},{"id":96341311,"identity":"0ed9499a-f53d-44b0-993d-d2558045779e","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":455976,"visible":true,"origin":"","legend":"","description":"","filename":"levwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/91223b8e93493a220c703cfb.png"},{"id":96367636,"identity":"d75b5b5a-6045-4a7b-9e27-aae1bf2e14bc","added_by":"auto","created_at":"2025-11-20 10:13:45","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155167,"visible":true,"origin":"","legend":"","description":"","filename":"levwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/0a771e54d22a5dcde872f742.png"},{"id":96366963,"identity":"f759958f-6cdd-43c6-90df-a73c8ba575c1","added_by":"auto","created_at":"2025-11-20 10:12:04","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142006,"visible":true,"origin":"","legend":"","description":"","filename":"linegraphbleuscores.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/8e8e87987f2daf207088535c.png"},{"id":96366064,"identity":"9ce27295-c40d-496d-9896-1984e4b01270","added_by":"auto","created_at":"2025-11-20 10:11:06","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423696,"visible":true,"origin":"","legend":"","description":"","filename":"map.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/a5154e36855cfb074dc2cdd7.png"},{"id":96341310,"identity":"f2ab85c4-59b6-417f-8c96-0908fd1fb679","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86729,"visible":true,"origin":"","legend":"","description":"","filename":"map2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/e97fd3d7c3d847101ab5b853.png"},{"id":96366758,"identity":"ff1ac3a0-1eb9-4bb1-bcaf-2e1247999587","added_by":"auto","created_at":"2025-11-20 10:11:52","extension":"pdf","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27278,"visible":true,"origin":"","legend":"","description":"","filename":"preinformed.drawio1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/b81e57c3af7b5c8754e59d76.pdf"},{"id":96366875,"identity":"f9df3b0f-58ab-4a4c-9ade-460bdcd18ddd","added_by":"auto","created_at":"2025-11-20 10:12:00","extension":"pdf","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27265,"visible":true,"origin":"","legend":"","description":"","filename":"preinformed.drawio.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/5b1ae8bea46205f82e6f3d46.pdf"},{"id":96366459,"identity":"3f096d14-de0f-4ca2-bcd1-6abdbfce952d","added_by":"auto","created_at":"2025-11-20 10:11:28","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45940,"visible":true,"origin":"","legend":"","description":"","filename":"preinformed.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/dc603498300431d4f49e6469.png"},{"id":96341302,"identity":"557206f0-9fdb-464a-bedc-ab0e23462d8e","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45863,"visible":true,"origin":"","legend":"","description":"","filename":"preinformed2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/e065a23eb4fd3c3066a73f5b.png"},{"id":96341342,"identity":"ccacc0c3-7239-41c8-b9fd-b76bd881745b","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"zip","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10251,"visible":true,"origin":"","legend":"","description":"","filename":"samples2.zip","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7d3c160687d323ff1c2613b2.zip"},{"id":96367607,"identity":"be613cc7-f915-4009-8556-5603f4bf6939","added_by":"auto","created_at":"2025-11-20 10:13:33","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":287315,"visible":true,"origin":"","legend":"","description":"","filename":"shami.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c2a72b07ef7c62796716adb8.png"},{"id":96341313,"identity":"853ac531-2047-4994-92b2-cb898bb144a4","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"bst","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/21c5c67b5d83eb28c7ea6fb6.bst"},{"id":96341321,"identity":"fe352354-3b76-4ad9-8520-90b11360012f","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"bst","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/99df861ae9dd1c57710102c2.bst"},{"id":96341343,"identity":"5e43d33e-665d-4d9f-9ce1-c3c8bc2c1897","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"pdf","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/772ac9f6bc95556fb1602932.pdf"},{"id":96367637,"identity":"da3d72b7-c1fa-42db-86f0-47e773281171","added_by":"auto","created_at":"2025-11-20 10:13:45","extension":"bst","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/06d61ff30105293c8e7f9d8b.bst"},{"id":96341308,"identity":"b29933f4-3890-4613-8ccd-5817ba3fd1f5","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"bst","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/e5b8633a888ce564198f17de.bst"},{"id":96341329,"identity":"0b3791b0-8161-4f56-896d-f30eed521e64","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"cls","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/73d06b0212d1eee17b5c5ceb.cls"},{"id":96366936,"identity":"f25b66f0-1d98-469d-bae9-6b7dc7e57042","added_by":"auto","created_at":"2025-11-20 10:12:02","extension":"bst","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/5a249822d47d117213fff189.bst"},{"id":96341319,"identity":"0f9db885-7684-4e71-b585-ce2c683ca546","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"bst","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/21e8a28c19916b9f8b288237.bst"},{"id":96366216,"identity":"b6d06ce0-a55d-4316-bd54-3a7aceeabd50","added_by":"auto","created_at":"2025-11-20 10:11:17","extension":"bst","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/f29473c1c98471fc4f36c456.bst"},{"id":96341353,"identity":"42d7d63a-8f6b-46de-bed2-07c47b723c0f","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"bst","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/4ddc30cb2b5047846cb784b7.bst"},{"id":96366978,"identity":"b80adcef-4448-4951-b0b7-617a857d68b0","added_by":"auto","created_at":"2025-11-20 10:12:04","extension":"bst","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/6321615317246ded2703f263.bst"},{"id":96341363,"identity":"a306acee-7487-4084-aae7-0e744b0c528b","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"pdf","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70329,"visible":true,"origin":"","legend":"","description":"","filename":"targamaDiagrammss.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7c422e815941b6e3dfd23c59.pdf"},{"id":96341315,"identity":"bfaf00cd-9c77-4eb9-8aa5-6fc8c08b7993","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":207299,"visible":true,"origin":"","legend":"","description":"","filename":"targamaDiagramm.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/d2ba18f4e99f4a66823a380a.png"},{"id":96341314,"identity":"72e80a21-7e43-443d-b2fa-47b018f2c2b2","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67484,"visible":true,"origin":"","legend":"","description":"","filename":"tranformer.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/bcc8ef4bfe508c46070e5396.png"},{"id":96366846,"identity":"1d9cec1a-733c-4423-acfc-d9819868ce60","added_by":"auto","created_at":"2025-11-20 10:11:56","extension":"pdf","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5263,"visible":true,"origin":"","legend":"","description":"","filename":"ubnlogo.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/09fb7a778fa60fa8e5ed4fc3.pdf"},{"id":96341325,"identity":"07829e95-485e-44f0-8e55-5ce162596caa","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"pdf","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c122e8e03e8f8938fd26097c.pdf"},{"id":96366277,"identity":"5a498326-62ee-4ee5-862e-aed0d6cce24d","added_by":"auto","created_at":"2025-11-20 10:11:20","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1146889,"visible":true,"origin":"","legend":"","description":"","filename":"Online1000115689.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7bb27bfe2d3bd6fe436c8497.png"},{"id":96366047,"identity":"a371203f-62ff-473e-ad64-f02497562f55","added_by":"auto","created_at":"2025-11-20 10:11:05","extension":"png","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":254769,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineIraqi.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/65753a28b87bad749598804a.png"},{"id":96341331,"identity":"0e203f9d-796d-46cc-9d83-9e02652dded4","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52496,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineScreenshot20251101at18.01.57.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7ed6e25d0d4814d2eec3969b.png"},{"id":96341346,"identity":"9d4537bb-d20b-4c09-a142-119f8aafe7cc","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106436,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineTARGAMADiagramm1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/d937bbbc1527968356b16e58.png"},{"id":96341335,"identity":"a8707f25-a51d-4c98-a7b2-cc99eded2e75","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88180,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineTARGAMAmodified.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/da95e6d16dfca32fe9349e9d.png"},{"id":96367617,"identity":"f95d9058-79e6-4f94-b555-9359d2b60499","added_by":"auto","created_at":"2025-11-20 10:13:37","extension":"png","order_by":57,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86041,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineTargamaDiagrammodified1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/60f78c05f649dee8ea3c9164.png"},{"id":96341316,"identity":"aa0ff081-4535-4818-b38a-630d2a4b21f5","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":58,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86075,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineTargamaDiagrammodified.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/02cb4ae6168d5186c34172c7.png"},{"id":96366059,"identity":"b8859363-5128-44a4-ae5e-ad371088ea6f","added_by":"auto","created_at":"2025-11-20 10:11:06","extension":"png","order_by":59,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":253304,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineYemeni.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/756cc0dd5e3b475dfb2b772f.png"},{"id":96341323,"identity":"5d0af67d-dbd9-449f-93d4-9585f379d9c8","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":60,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49516,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineYouTubedata1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/ecebba6f9c05b6b52dba01e7.png"},{"id":96341356,"identity":"dea3695a-aa73-4ead-9010-12dd9dd3cc85","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":61,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":263351,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineall.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/09333122a86a615850c9cd1a.png"},{"id":96341339,"identity":"29b7a91f-e7fb-4995-aaa5-da0f7efd2f74","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":62,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":271171,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedarija.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/00cb2259486305a0867fcc91.png"},{"id":96366955,"identity":"9d9efb0d-bdb9-4067-b458-ef7e4633a892","added_by":"auto","created_at":"2025-11-20 10:12:03","extension":"png","order_by":63,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":391762,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedarijawc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/972e866a1b5da536a38322b9.png"},{"id":96341351,"identity":"98218417-665f-492a-9d53-098545c11875","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":64,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37329,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedistr.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/ce8f7aee421d03991f918d4c.png"},{"id":96366818,"identity":"1e0f5aea-d739-4676-8349-267329ba615c","added_by":"auto","created_at":"2025-11-20 10:11:56","extension":"png","order_by":65,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":365725,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineegwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c00b39b549b120134290d86d.png"},{"id":96341354,"identity":"8c12d578-6493-4e60-ac48-13ccb308d4ba","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":66,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":269766,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineegy.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/01cadb2c18478bce1944899d.png"},{"id":96367172,"identity":"fa89b5b1-8458-4ae7-aa39-d3d0a8964612","added_by":"auto","created_at":"2025-11-20 10:12:15","extension":"png","order_by":67,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":262146,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegulf.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/1ec10173487e8168f5b2580b.png"},{"id":96366410,"identity":"9155a654-db77-450e-8f17-0e65e5c84951","added_by":"auto","created_at":"2025-11-20 10:11:25","extension":"png","order_by":68,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":384786,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinelevwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/fbb0e4575ced49d23f89e071.png"},{"id":96341355,"identity":"e0e6df8f-a903-4b2c-ac15-64bd2772345a","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":69,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":371876,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinelevwc.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/2804d1779ed39d5b9c7c7ea3.png"},{"id":96366090,"identity":"87ac5461-0bd0-49ee-94ed-3eb78ff4205c","added_by":"auto","created_at":"2025-11-20 10:11:10","extension":"png","order_by":70,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123654,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinelinegraphbleuscores.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c75ba5971235d3cdb24a7977.png"},{"id":96341350,"identity":"a4888648-94c8-4656-9547-506877229fc5","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":71,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":372833,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinemap.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/0fbebdc45ea11264c97c1eec.png"},{"id":96366951,"identity":"7297f89c-fc7c-4fc9-8139-7a6600891cd1","added_by":"auto","created_at":"2025-11-20 10:12:03","extension":"png","order_by":72,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86711,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinemap2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/c96cb9cd7ed9d3f40a4da920.png"},{"id":96366511,"identity":"c1212ba5-5f83-4b82-ad62-512a82208bb9","added_by":"auto","created_at":"2025-11-20 10:11:31","extension":"png","order_by":73,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43487,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinepreinformed.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/a3201899f735a6b22fe941ee.png"},{"id":96341349,"identity":"98775f11-a967-4fa7-9cf8-3d775b3cc381","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":74,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43268,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinepreinformed2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/44da12aa070042e911c0002a.png"},{"id":96341360,"identity":"086ffb55-638d-48a0-a6c1-76263e6d0d6f","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"png","order_by":75,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":255875,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineshami.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/7f432206a95d0c4961e75f99.png"},{"id":96341330,"identity":"7d3622ba-c56a-4b3f-8992-ba333357482a","added_by":"auto","created_at":"2025-11-20 04:51:19","extension":"png","order_by":76,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108394,"visible":true,"origin":"","legend":"","description":"","filename":"OnlinetargamaDiagramm.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/8337df437597c09d0ca4a420.png"},{"id":96367317,"identity":"4562c06f-505b-4bb3-b038-b99a4e7cb195","added_by":"auto","created_at":"2025-11-20 10:12:31","extension":"png","order_by":77,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64761,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinetranformer.png","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/9ad78a3a6b35fcacfb4efe66.png"},{"id":96341348,"identity":"b81e3060-6993-4658-8eb4-d9b849e31aa9","added_by":"auto","created_at":"2025-11-20 04:51:20","extension":"xml","order_by":78,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99786,"visible":true,"origin":"","legend":"","description":"","filename":"10abf680cfec4f8e9030edc565b119171structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/e38f92a06f2f0cf69ca00ccd.xml"},{"id":96453363,"identity":"b8650d67-7f99-49b5-8eb7-59624ab41d45","added_by":"auto","created_at":"2025-11-21 09:59:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":783701,"visible":true,"origin":"","legend":"","description":"","filename":"AFrameworkforTranslatingDialectalArabicwithGenerativeLanguageModels11.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1_covered_5bc3b586-06a1-41db-913c-0e0424087465.pdf"},{"id":96341283,"identity":"c94f768e-3e83-468a-8fba-abdcbe523a53","added_by":"auto","created_at":"2025-11-20 04:51:18","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":10251,"visible":true,"origin":"","legend":"","description":"","filename":"samples2.zip","url":"https://assets-eu.researchsquare.com/files/rs-8007453/v1/23ba5a5163b395cf9c4027b3.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dialectal Arabic, Machine Translation, Benchmark, Generative Language Models","lastPublishedDoi":"10.21203/rs.3.rs-8007453/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8007453/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Arabic, one of the world’s most widely spoken languages, is marked by extensive dialectal variation that often differs significantly from Modern Standard Arabic (MSA) and from other dialects. This linguistic diversity presents considerable challenges for machine translation systems, especially when translating dialectal Arabic into MSA or English. Addressing this gap, this work introduces TARGAMA, a novel benchmark dataset and framework designed to improve dialectal Arabic-English translation by leveraging state-of-the-art generative language models. As part of this work, we develop the largest known multi-dialectal Arabic-English parallel corpus, covering six major dialects. Using this dataset, we evaluate a variety of generative language models and propose a unified framework for dialect-aware translation. Our approach demonstrates strong performance across dialects and offers a scalable solution for improving translation quality in low-resource and linguistically diverse settings.","manuscriptTitle":"TARGAMA: A Novel Benchmark Dataset and Framework for Translating Dialectal Arabic to English with Generative Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-20 04:51:13","doi":"10.21203/rs.3.rs-8007453/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-12T08:03:11+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-12T07:27:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-09T09:40:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-09T03:15:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-26T12:26:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-15T07:13:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"143485964991954684215124383118197015576","date":"2025-11-13T06:18:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"260312801917944225613488057330869832125","date":"2025-11-13T02:11:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162306681761560440728028372312320668335","date":"2025-11-13T01:17:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"304068152125790934300879532955782088086","date":"2025-11-11T10:59:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"287384655329713075695151991673066907553","date":"2025-11-11T05:20:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"117859130977807334997260005257931327711","date":"2025-11-11T04:14:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-10T20:06:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-10T13:43:36+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-07T11:26:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-11-01T18:26:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"03d0e7ea-ebde-4b35-af19-fae2fd367acf","owner":[],"postedDate":"November 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-15T12:53:29+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-20 04:51:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8007453","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8007453","identity":"rs-8007453","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}