{"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/strong-baselines-for-complex-word","title":"Strong Baselines for Complex Word Identification across Multiple Languages","arxiv_id":"1904.05953","date":"2019-04-11","proceeding":"NAACL 2019 6","authors":["Pierre Finnimore","Elisabeth Fritzsch","Daniel King","Alison Sneyd","Aneeq Ur Rehman","Fernando Alva-Manchego","Andreas Vlachos"],"abstract":"Complex Word Identification (CWI) is the task of identifying which words or\nphrases in a sentence are difficult to understand by a target audience. The\nlatest CWI Shared Task released data for two settings: monolingual (i.e. train\nand test in the same language) and cross-lingual (i.e. test in a language not\nseen during training). The best monolingual models relied on language-dependent\nfeatures, which do not generalise in the cross-lingual setting, while the best\ncross-lingual model used neural networks with multi-task learning. In this\npaper, we present monolingual and cross-lingual CWI models that perform as well\nas (or better than) most models submitted to the latest CWI Shared Task. We\nshow that carefully selected features and simple learning models can achieve\nstate-of-the-art performance, and result in strong baselines for future\ndevelopment in this area. Finally, we discuss how inconsistencies in the\nannotation of the data can explain some of the results obtained.","url_abs":"http://arxiv.org/abs/1904.05953v1","url_pdf":"http://arxiv.org/pdf/1904.05953v1.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":"strong-baselines-for-complex-word","repo_url":"https://github.com/sheffieldnlp/cwi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"complex-word-identification","task_name":"Complex Word Identification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05953","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}