[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273463-105":59,"doc-detail-273463-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","indicqe-ape-a-consolidated-benchmark-for-quality-estimation-and-automatic-post-editing-for-indic-languages","INDICQE-APE - A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages","","Indic quality estimation (QE) and automatic post-editing (APE) datasets are fragmented across separate releases, limiting unified training and evaluation across tasks and language pairs. INDICQE-APE consolidates the WMT 2020–2024 shared-task lineage with an extended English–Malayalam resource into 126,754 instances across nine directional pairs. The benchmark aligns up to four label types per segment, including direct assessment, post-edit, word-level tags, and error explanations, with test stratification on four difficulty axes. Baselines evaluate six prompted LLMs and three COMET metrics for segment-level QE, and three systems for APE.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/indicqe-ape-a-consolidated-benchmark-for-quality-estimation-and-automatic-post-editing-for-indic-languages/273463/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/indicqe-ape-a-consolidated-benchmark-for-quality-estimation-and-automatic-post-editing-for-indic-languages/273463.png","ImageObject",300,407,{"name":92,"@type":93},"Ava Thompson","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does INDICQE-APE address in Indic machine translation evaluation?","Question",{"text":112,"@type":113},"It addresses the fragmentation of QE and APE data across incompatible releases, which otherwise forces rebuilding corpora to train and evaluate across tasks and language pairs. It also supports a more reliable measurement than a single learned scalar across languages.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What information is aligned in each INDICQE-APE instance?",{"text":117,"@type":113},"Each instance can include a direct assessment, a post-edit, word-level tags, and an error explanation, aligned on the same segment so QE, APE, and explainable QE can be studied without re-aligning corpora.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the benchmark evaluated and what models are used?",{"text":121,"@type":113},"The study benchmarks six prompted LLMs and three COMET metrics for segment-level QE, and evaluates three systems on APE. It reports correlation and output-format compliance and analyzes how unedited machine translation compares with APE systems across pairs.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},273463,1789471541,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},1649267921044,"https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1786009248482753345","INDICQE-APE: A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages  \nDiptesh Kanojia 1 Archchana Sindhujan 1 Sourabh Deoghare2 Daria Sokova 1 Shenbin Qian3 Girish Koushik 1 Tharindu Ranasinghe4 Constantin Orăsan 1 Chrysoula Zerva5 Ricardo Rei6 ,7 Frederic Blain8 André F. T. Martins5  \nMarco Turchi9 Matteo Negri 10  \nAnoop Kunchukuttan 11 , 12 Mitesh M. Khapra 11 , 12 Pushpak Bhattacharyya2  \n1University of Surrey 2IIT Bombay 3University of Oslo 4Lancaster University  \n5Instituto de Telecomunicações & Instituto Superior Técnico, University of Lisbon  \n6 Sword Health 7INESC-ID 8Tilburg University 9Zoom Communications  \n10Fondazione Bruno Kessler 11Bodhan AI 12AI4Bharat, IIT Madras  \n[d.kanojia@surrey.ac.uk](d.kanojia@surrey.ac.uk)  \narXiv : 2608 . 16344v 3 [cs .CL] 12 Sep 2026  \nAbstract  \nIndic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks and language pairs on one footing. We consolidate the WMT 2020–2024 shared-task lineage with an extended English-Malayalam resource into INDICQE-APE: 126 ,754 instances over nine directional pairs, with up to four label types aligned on the same segment, a direct assessment, a human post-edit, word-level tags and an error explanation, and a test set stratified over four difficulty axes. We benchmark six prompted LLMs and three COMET metrics on segment-level QE, and three systems on APE.  \nTwo of the axes are defined partly on direct assessment and select a compressed slice of it. Segments whose segment-level and tokenlevel signals disagree are ranked below equally scored segments of the same language. Fourshot prompting costs every model at or below  \n3.4B both correlation and output-format compliance. Unedited MT beats every APE system we run on three of the four pairs. The benchmark1 and code2 are released.  \n1 Introduction  \nReference-free evaluation of machine translation, scoring a translation without a human reference (QE) and repairing it (APE), remains an open problem for Indic and other low-resource languages for two compounding reasons. The data is fragmented: direct assessments, post-edits, word-level tags and explanations live in separate shared-task releases with incompatible schemas, splits and provenance,  \n1[https://huggingface.co/datasets/surrey-nlp/](https://huggingface.co/datasets/surrey-nlp/)  \nIndicQE-APE 2[https://github.com/surrey-nlp/IndicQE-APE](https://github.com/surrey-nlp/IndicQE-APE)  \nso training and evaluating across tasks and pairs means rebuilding the corpus first. In addition, evaluation on the data that does exist falls back on a single learned scalar whose behaviour across languages is rarely checked.  \nWe address the first with a resource and the second with a measurement on it. INDICQEAPE unifies the WMT 2020–2024 QE and APE shared-task data for Indic pairs with an extended English→ Malayalam resource into one release of 126 ,754 instances over nine directional pairs, sliceable by task and by language pair (Table 3) . The label types are aligned on the same items: one instance may carry a direct assessment, a post-edit, word-level tags and an error explanation at once, so QE, APE and explainable QE can be studied without re-aligning corpora. Every test segment is flagged on each of four difficulty axes its labels can express. Appendix A places the release against the shared-task and metric literature it consolidates.  \nWe report baselines for segment-level QE over all nine pairs and for APE over four. CometKiwi-XL (Rei et al., 2023) has the highest within-language segment correlation of the models we evaluate and the weakest cross-lingual agreement of the three trained metrics: its per-language offset moves against quality, where the offsets of the other two move with it, and pooling pairs costs it more than either. Within-language skill and cross-lingual comparability are separate properties, and a","cbCaidOgUPGmPvxa","https://ap.wps.com/l/cbCaidOgUPGmPvxa","pdf",305732,27,"English","# Abstract\n# Introduction\n# The INDICQE-APE Benchmark\n## Dataset consolidation and label alignment\n## Difficulty axes and measurement design","[{\"question\":\"What problem does INDICQE-APE address in Indic machine translation evaluation?\",\"answer\":\"It addresses the fragmentation of QE and APE data across incompatible releases, which otherwise forces rebuilding corpora to train and evaluate across tasks and language pairs. It also supports a more reliable measurement than a single learned scalar across languages.\"},{\"question\":\"What information is aligned in each INDICQE-APE instance?\",\"answer\":\"Each instance can include a direct assessment, a post-edit, word-level tags, and an error explanation, aligned on the same segment so QE, APE, and explainable QE can be studied without re-aligning corpora.\"},{\"question\":\"How is the benchmark evaluated and what models are used?\",\"answer\":\"The study benchmarks six prompted LLMs and three COMET metrics for segment-level QE, and evaluates three systems on APE. It reports correlation and output-format compliance and analyzes how unedited machine translation compares with APE systems across pairs.\"}]","INDICQE-APE - A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages | PDF",68]