{"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/assessing-crosslingual-discourse-relations-in","title":"Assessing Crosslingual Discourse Relations in Machine Translation","arxiv_id":"1810.03148","date":"2018-10-07","proceeding":null,"authors":["Karin Sim Smith","Lucia Specia"],"abstract":"In an attempt to improve overall translation quality, there has been an\nincreasing focus on integrating more linguistic elements into Machine\nTranslation (MT). While significant progress has been achieved, especially\nrecently with neural models, automatically evaluating the output of such\nsystems is still an open problem. Current practice in MT evaluation relies on a\nsingle reference translation, even though there are many ways of translating a\nparticular text, and it tends to disregard higher level information such as\ndiscourse. We propose a novel approach that assesses the translated output\nbased on the source text rather than the reference translation, and measures\nthe extent to which the semantics of the discourse elements (discourse\nrelations, in particular) in the source text are preserved in the MT output.\nThe challenge is to detect the discourse relations in the source text and\ndetermine whether these relations are correctly transferred crosslingually to\nthe target language -- without a reference translation. This methodology could\nbe used independently for discourse-level evaluation, or as a component in\nother metrics, at a time where substantial amounts of MT are online and would\nbenefit from evaluation where the source text serves as a benchmark.","url_abs":"http://arxiv.org/abs/1810.03148v1","url_pdf":"http://arxiv.org/pdf/1810.03148v1.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":"assessing-crosslingual-discourse-relations-in","repo_url":"https://github.com/cairouchong/discourse-phenomena","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}