{"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/the-argument-reasoning-comprehension-task","title":"The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants","arxiv_id":"1708.01425","date":"2017-08-04","proceeding":"NAACL 2018 6","authors":["Ivan Habernal","Henning Wachsmuth","Iryna Gurevych","Benno Stein"],"abstract":"Reasoning is a crucial part of natural language argumentation. To comprehend\nan argument, one must analyze its warrant, which explains why its claim follows\nfrom its premises. As arguments are highly contextualized, warrants are usually\npresupposed and left implicit. Thus, the comprehension does not only require\nlanguage understanding and logic skills, but also depends on common sense. In\nthis paper we develop a methodology for reconstructing warrants systematically.\nWe operationalize it in a scalable crowdsourcing process, resulting in a freely\nlicensed dataset with warrants for 2k authentic arguments from news comments.\nOn this basis, we present a new challenging task, the argument reasoning\ncomprehension task. Given an argument with a claim and a premise, the goal is\nto choose the correct implicit warrant from two options. Both warrants are\nplausible and lexically close, but lead to contradicting claims. A solution to\nthis task will define a substantial step towards automatic warrant\nreconstruction. However, experiments with several neural attention and language\nmodels reveal that current approaches do not suffice.","url_abs":"http://arxiv.org/abs/1708.01425v4","url_pdf":"http://arxiv.org/pdf/1708.01425v4.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":"the-argument-reasoning-comprehension-task","repo_url":"https://github.com/UKPLab/argument-reasoning-comprehension-task","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"the-argument-reasoning-comprehension-task","repo_url":"https://github.com/galsang/SemEval2018-task12","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"the-argument-reasoning-comprehension-task","repo_url":"https://github.com/hongking9/SemEval-2018-task12","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01425","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}