{"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/dataset-for-automatic-summarization-of","title":"Dataset for Automatic Summarization of Russian News","arxiv_id":"2006.11063","date":"2020-06-19","proceeding":null,"authors":["Ilya Gusev"],"abstract":"Automatic text summarization has been studied in a variety of domains and languages. However, this does not hold for the Russian language. To overcome this issue, we present Gazeta, the first dataset for summarization of Russian news. We describe the properties of this dataset and benchmark several extractive and abstractive models. We demonstrate that the dataset is a valid task for methods of text summarization for Russian. Additionally, we prove the pretrained mBART model to be useful for Russian text summarization.","url_abs":"https://arxiv.org/abs/2006.11063v4","url_pdf":"https://arxiv.org/pdf/2006.11063v4.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":"dataset-for-automatic-summarization-of","repo_url":"https://github.com/IlyaGusev/gazeta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dataset-for-automatic-summarization-of","repo_url":"https://github.com/IlyaGusev/summarus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"text-summarization","task_name":"Text Summarization"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"mbart","method_name":"mBART"}],"datasets_introduced":[{"slug":"gazeta","name":"Gazeta","full_name":null}],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-gazeta","task":"Text Summarization","dataset":"Gazeta","model":"Finetuned mBART","rank_in_archive_order":1,"of":1,"metrics":{"BLEU":"12.4","Meteor":"25.7","ROUGE-1":"32.1","ROUGE-2":"14.2","ROUGE-L":"27.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.11063","atlas_url":"https://app.syntology.ai/?focus=2006.11063","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}