{"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/context-aware-prediction-of-derivational-word","title":"Context-Aware Prediction of Derivational Word-forms","arxiv_id":"1702.06675","date":"2017-02-22","proceeding":"EACL 2017 4","authors":["Ekaterina Vylomova","Ryan Cotterell","Timothy Baldwin","Trevor Cohn"],"abstract":"Derivational morphology is a fundamental and complex characteristic of\nlanguage. In this paper we propose the new task of predicting the derivational\nform of a given base-form lemma that is appropriate for a given context. We\npresent an encoder--decoder style neural network to produce a derived form\ncharacter-by-character, based on its corresponding character-level\nrepresentation of the base form and the context. We demonstrate that our model\nis able to generate valid context-sensitive derivations from known base forms,\nbut is less accurate under a lexicon agnostic setting.","url_abs":"http://arxiv.org/abs/1702.06675v1","url_pdf":"http://arxiv.org/pdf/1702.06675v1.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":"context-aware-prediction-of-derivational-word","repo_url":"https://github.com/ivri/dmorph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"form","task_name":"Form"},{"task_slug":"lemma","task_name":"LEMMA"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.06675","atlas_url":"https://app.syntology.ai/?focus=1702.06675","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}