{"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/extracting-parallel-sentences-with","title":"Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation","arxiv_id":"1806.05559","date":"2018-06-13","proceeding":"COLING 2018 8","authors":["Francis Grégoire","Philippe Langlais"],"abstract":"Parallel sentence extraction is a task addressing the data sparsity problem\nfound in multilingual natural language processing applications. We propose a\nbidirectional recurrent neural network based approach to extract parallel\nsentences from collections of multilingual texts. Our experiments with noisy\nparallel corpora show that we can achieve promising results against a\ncompetitive baseline by removing the need of specific feature engineering or\nadditional external resources. To justify the utility of our approach, we\nextract sentence pairs from Wikipedia articles to train machine translation\nsystems and show significant improvements in translation performance.","url_abs":"http://arxiv.org/abs/1806.05559v2","url_pdf":"http://arxiv.org/pdf/1806.05559v2.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":"extracting-parallel-sentences-with","repo_url":"https://github.com/FrancisGregoire/parSentExtract","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.05559","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}