{"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/paracrawl-web-scale-acquisition-of-parallel","title":"ParaCrawl: Web-Scale Acquisition of Parallel Corpora","arxiv_id":null,"date":"2020-07-01","proceeding":"ACL 2020 6","authors":["Marta Ba{\\~n}{\\'o}n","Pin-zhen Chen","Barry Haddow","Kenneth Heafield","Hieu Hoang","Miquel Espl{\\`a}-Gomis","Mikel L. Forcada","Amir Kamran","Faheem Kirefu","Philipp Koehn","Sergio Ortiz Rojas","Leopoldo Pla Sempere","Gema Ram{\\'\\i}rez-S{\\'a}nchez","Elsa Sarr{\\'\\i}as","Marek Strelec","Brian Thompson","William Waites","Dion Wiggins","Jaume Zaragoza"],"abstract":"We report on methods to create the largest publicly available parallel corpora by crawling the web, using open source software. We empirically compare alternative methods and publish benchmark data sets for sentence alignment and sentence pair filtering. We also describe the parallel corpora released and evaluate their quality and their usefulness to create machine translation systems.","url_abs":"https://aclanthology.org/2020.acl-main.417","url_pdf":"https://aclanthology.org/2020.acl-main.417.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":"paracrawl-web-scale-acquisition-of-parallel","repo_url":"https://github.com/bitextor/bitextor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"paracrawl-web-scale-acquisition-of-parallel","repo_url":"https://github.com/marian-nmt/marian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"parallel-corpus-mining","task_name":"Parallel Corpus Mining"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"paracrawl","name":"ParaCrawl","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}