{"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/translations-as-additional-contexts-for","title":"Translations as Additional Contexts for Sentence Classification","arxiv_id":"1806.05516","date":"2018-06-14","proceeding":null,"authors":["Reinald Kim Amplayo","Kyungjae Lee","Jinyeong Yeo","Seung-won Hwang"],"abstract":"In sentence classification tasks, additional contexts, such as the\nneighboring sentences, may improve the accuracy of the classifier. However,\nsuch contexts are domain-dependent and thus cannot be used for another\nclassification task with an inappropriate domain. In contrast, we propose the\nuse of translated sentences as context that is always available regardless of\nthe domain. We find that naive feature expansion of translations gains only\nmarginal improvements and may decrease the performance of the classifier, due\nto possible inaccurate translations thus producing noisy sentence vectors. To\nthis end, we present multiple context fixing attachment (MCFA), a series of\nmodules attached to multiple sentence vectors to fix the noise in the vectors\nusing the other sentence vectors as context. We show that our method performs\ncompetitively compared to previous models, achieving best classification\nperformance on multiple data sets. We are the first to use translations as\ndomain-free contexts for sentence classification.","url_abs":"http://arxiv.org/abs/1806.05516v1","url_pdf":"http://arxiv.org/pdf/1806.05516v1.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":"translations-as-additional-contexts-for","repo_url":"https://github.com/rktamplayo/MCFA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"subjectivity-analysis","task_name":"Subjectivity Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/subjectivity-analysis-on-subj","task":"Subjectivity Analysis","dataset":"SUBJ","model":"CNN+MCFA","rank_in_archive_order":7,"of":19,"metrics":{"Accuracy":"94.80"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-trec-6","task":"Text Classification","dataset":"TREC-6","model":"CNN+MCFA","rank_in_archive_order":7,"of":19,"metrics":{"Error":"4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}