{"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/character-level-models-versus-morphology-in","title":"Character-Level Models versus Morphology in Semantic Role Labeling","arxiv_id":"1805.11937","date":"2018-05-30","proceeding":"ACL 2018 7","authors":["Gözde Gül Şahin","Mark Steedman"],"abstract":"Character-level models have become a popular approach specially for their\naccessibility and ability to handle unseen data. However, little is known on\ntheir ability to reveal the underlying morphological structure of a word, which\nis a crucial skill for high-level semantic analysis tasks, such as semantic\nrole labeling (SRL). In this work, we train various types of SRL models that\nuse word, character and morphology level information and analyze how\nperformance of characters compare to words and morphology for several\nlanguages. We conduct an in-depth error analysis for each morphological\ntypology and analyze the strengths and limitations of character-level models\nthat relate to out-of-domain data, training data size, long range dependencies\nand model complexity. Our exhaustive analyses shed light on important\ncharacteristics of character-level models and their semantic capability.","url_abs":"http://arxiv.org/abs/1805.11937v1","url_pdf":"http://arxiv.org/pdf/1805.11937v1.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":"character-level-models-versus-morphology-in","repo_url":"https://github.com/gozdesahin/Subword_Semantic_Role_Labeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.11937","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}