{"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/reference-less-quality-estimation-of-text","title":"Reference-less Quality Estimation of Text Simplification Systems","arxiv_id":"1901.10746","date":"2019-01-30","proceeding":"WS 2018 11","authors":["Louis Martin","Samuel Humeau","Pierre-Emmanuel Mazaré","Antoine Bordes","Éric Villemonte de la Clergerie","Benoît Sagot"],"abstract":"The evaluation of text simplification (TS) systems remains an open challenge.\nAs the task has common points with machine translation (MT), TS is often\nevaluated using MT metrics such as BLEU. However, such metrics require high\nquality reference data, which is rarely available for TS. TS has the advantage\nover MT of being a monolingual task, which allows for direct comparisons to be\nmade between the simplified text and its original version. In this paper, we\ncompare multiple approaches to reference-less quality estimation of\nsentence-level text simplification systems, based on the dataset used for the\nQATS 2016 shared task. We distinguish three different dimensions:\ngram-maticality, meaning preservation and simplicity. We show that n-gram-based\nMT metrics such as BLEU and METEOR correlate the most with human judgment of\ngrammaticality and meaning preservation, whereas simplicity is best evaluated\nby basic length-based metrics.","url_abs":"http://arxiv.org/abs/1901.10746v1","url_pdf":"http://arxiv.org/pdf/1901.10746v1.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":"reference-less-quality-estimation-of-text","repo_url":"https://github.com/facebookresearch/text-simplification-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-simplification","task_name":"Text Simplification"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"ts","method_name":"TS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.10746","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}