{"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/snu_ids-at-semeval-2018-task-12-sentence","title":"SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension","arxiv_id":"1805.07049","date":"2018-05-18","proceeding":"SEMEVAL 2018 6","authors":["Taeuk Kim","Jihun Choi","Sang-goo Lee"],"abstract":"We present a novel neural architecture for the Argument Reasoning\nComprehension task of SemEval 2018. It is a simple neural network consisting of\nthree parts, collectively judging whether the logic built on a set of given\nsentences (a claim, reason, and warrant) is plausible or not. The model\nutilizes contextualized word vectors pre-trained on large machine translation\n(MT) datasets as a form of transfer learning, which can help to mitigate the\nlack of training data. Quantitative analysis shows that simply leveraging LSTMs\ntrained on MT datasets outperforms several baselines and non-transferred\nmodels, achieving accuracies of about 70% on the development set and about 60%\non the test set.","url_abs":"http://arxiv.org/abs/1805.07049v1","url_pdf":"http://arxiv.org/pdf/1805.07049v1.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":"snu_ids-at-semeval-2018-task-12-sentence","repo_url":"https://github.com/galsang/SemEval2018-task12","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"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}