{"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-sub-character-architecture-for-korean","title":"A Sub-Character Architecture for Korean Language Processing","arxiv_id":"1707.06341","date":"2017-07-20","proceeding":"EMNLP 2017 9","authors":["Karl Stratos"],"abstract":"We introduce a novel sub-character architecture that exploits a unique\ncompositional structure of the Korean language. Our method decomposes each\ncharacter into a small set of primitive phonetic units called jamo letters from\nwhich character- and word-level representations are induced. The jamo letters\ndivulge syntactic and semantic information that is difficult to access with\nconventional character-level units. They greatly alleviate the data sparsity\nproblem, reducing the observation space to 1.6% of the original while\nincreasing accuracy in our experiments. We apply our architecture to dependency\nparsing and achieve dramatic improvement over strong lexical baselines.","url_abs":"http://arxiv.org/abs/1707.06341v2","url_pdf":"http://arxiv.org/pdf/1707.06341v2.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-sub-character-architecture-for-korean","repo_url":"https://github.com/karlstratos/koreannet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}