{"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-morphology-aware-network-for-morphological","title":"A Morphology-aware Network for Morphological Disambiguation","arxiv_id":"1702.03654","date":"2017-02-13","proceeding":null,"authors":["Eray Yildiz","Caglar Tirkaz","H. Bahadir Sahin","Mustafa Tolga Eren","Ozan Sonmez"],"abstract":"Agglutinative languages such as Turkish, Finnish and Hungarian require\nmorphological disambiguation before further processing due to the complex\nmorphology of words. A morphological disambiguator is used to select the\ncorrect morphological analysis of a word. Morphological disambiguation is\nimportant because it generally is one of the first steps of natural language\nprocessing and its performance affects subsequent analyses. In this paper, we\npropose a system that uses deep learning techniques for morphological\ndisambiguation. Many of the state-of-the-art results in computer vision, speech\nrecognition and natural language processing have been obtained through deep\nlearning models. However, applying deep learning techniques to morphologically\nrich languages is not well studied. In this work, while we focus on Turkish\nmorphological disambiguation we also present results for French and German in\norder to show that the proposed architecture achieves high accuracy with no\nlanguage-specific feature engineering or additional resource. In the\nexperiments, we achieve 84.12, 88.35 and 93.78 morphological disambiguation\naccuracy among the ambiguous words for Turkish, German and French respectively.","url_abs":"http://arxiv.org/abs/1702.03654v1","url_pdf":"http://arxiv.org/pdf/1702.03654v1.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-morphology-aware-network-for-morphological","repo_url":"https://github.com/hbahadirsahin/text_categorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"morphological-analysis","task_name":"Morphological Analysis"},{"task_slug":"morphological-disambiguation","task_name":"Morphological Disambiguation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}