{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/indicxtreme-a-multi-task-benchmark-for","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","arxiv_id":"2212.05409","date":"2022-12-11","proceeding":null,"authors":["Sumanth Doddapaneni","Rahul Aralikatte","Gowtham Ramesh","Shreya Goyal","Mitesh M. Khapra","Anoop Kunchukuttan","Pratyush Kumar"],"abstract":"Building Natural Language Understanding (NLU) capabilities for Indic languages, which have a collective speaker base of more than one billion speakers is absolutely crucial. In this work, we aim to improve the NLU capabilities of Indic languages by making contributions along 3 important axes (i) monolingual corpora (ii) NLU testsets (iii) multilingual LLMs focusing on Indic languages. Specifically, we curate the largest monolingual corpora, IndicCorp, with 20.9B tokens covering 24 languages from 4 language families - a 2.3x increase over prior work, while supporting 12 additional languages. Next, we create a human-supervised benchmark, IndicXTREME, consisting of nine diverse NLU tasks covering 20 languages. Across languages and tasks, IndicXTREME contains a total of 105 evaluation sets, of which 52 are new contributions to the literature. To the best of our knowledge, this is the first effort towards creating a standard benchmark for Indic languages that aims to test the multilingual zero-shot capabilities of pretrained language models. Finally, we train IndicBERT v2, a state-of-the-art model supporting all the languages. Averaged across languages and tasks, the model achieves an absolute improvement of 2 points over a strong baseline. The data and models are available at https://github.com/AI4Bharat/IndicBERT.","url_abs":"https://arxiv.org/abs/2212.05409v3","url_pdf":"https://arxiv.org/pdf/2212.05409v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"indicxtreme-a-multi-task-benchmark-for","repo_url":"https://github.com/ai4bharat/indicbert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"xlm-r","task_name":"XLM-R"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"test","method_name":"Test"},{"method_slug":"xlm-r","method_name":"XLM-R"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.05409","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}