{"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/a-characterwise-windowed-approach-to-hebrew","title":"A Characterwise Windowed Approach to Hebrew Morphological Segmentation","arxiv_id":"1808.07214","date":"2018-08-22","proceeding":"WS 2018 10","authors":["Amir Zeldes"],"abstract":"This paper presents a novel approach to the segmentation of orthographic word\nforms in contemporary Hebrew, focusing purely on splitting without carrying out\nmorphological analysis or disambiguation. Casting the analysis task as\ncharacter-wise binary classification and using adjacent character and\nword-based lexicon-lookup features, this approach achieves over 98% accuracy on\nthe benchmark SPMRL shared task data for Hebrew, and 97% accuracy on a new out\nof domain Wikipedia dataset, an improvement of ~4% and 5% over previous state\nof the art performance.","url_abs":"http://arxiv.org/abs/1808.07214v2","url_pdf":"http://arxiv.org/pdf/1808.07214v2.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":"a-characterwise-windowed-approach-to-hebrew","repo_url":"https://github.com/amir-zeldes/RFTokenizer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"morphological-analysis","task_name":"Morphological Analysis"},{"task_slug":"text-segmentation","task_name":"Text Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"wiki5k-hebrew-segmentation","name":"Wiki5K Hebrew segmentation","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.07214","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}