{"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/neural-end-to-end-learning-for-computational","title":"Neural End-to-End Learning for Computational Argumentation Mining","arxiv_id":"1704.06104","date":"2017-04-20","proceeding":"ACL 2017 7","authors":["Steffen Eger","Johannes Daxenberger","Iryna Gurevych"],"abstract":"We investigate neural techniques for end-to-end computational argumentation\nmining (AM). We frame AM both as a token-based dependency parsing and as a\ntoken-based sequence tagging problem, including a multi-task learning setup.\nContrary to models that operate on the argument component level, we find that\nframing AM as dependency parsing leads to subpar performance results. In\ncontrast, less complex (local) tagging models based on BiLSTMs perform robustly\nacross classification scenarios, being able to catch long-range dependencies\ninherent to the AM problem. Moreover, we find that jointly learning 'natural'\nsubtasks, in a multi-task learning setup, improves performance.","url_abs":"http://arxiv.org/abs/1704.06104v2","url_pdf":"http://arxiv.org/pdf/1704.06104v2.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":"neural-end-to-end-learning-for-computational","repo_url":"https://github.com/UKPLab/acl2017-neural_end2end_AM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"neural-end-to-end-learning-for-computational","repo_url":"https://github.com/achernodub/targer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.06104","atlas_url":"https://app.syntology.ai/?focus=1704.06104","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}