{"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/nlitrans-at-semeval-2018-task-12-transfer-of","title":"NLITrans at SemEval-2018 Task 12: Transfer of Semantic Knowledge for Argument Comprehension","arxiv_id":"1804.08266","date":"2018-04-23","proceeding":"SEMEVAL 2018 6","authors":["Tim Niven","Hung-Yu Kao"],"abstract":"The Argument Reasoning Comprehension Task requires significant language\nunderstanding and complex reasoning over world knowledge. We focus on transfer\nof a sentence encoder to bootstrap more complicated models given the small size\nof the dataset. Our best model uses a pre-trained BiLSTM to encode input\nsentences, learns task-specific features for the argument and warrants, then\nperforms independent argument-warrant matching. This model achieves mean test\nset accuracy of 64.43%. Encoder transfer yields a significant gain to our best\nmodel over random initialization. Independent warrant matching effectively\ndoubles the size of the dataset and provides additional regularization. We\ndemonstrate that regularization comes from ignoring statistical correlations\nbetween warrant features and position. We also report an experiment with our\nbest model that only matches warrants to reasons, ignoring claims. Relatively\nlow performance degradation suggests that our model is not necessarily learning\nthe intended task.","url_abs":"http://arxiv.org/abs/1804.08266v1","url_pdf":"http://arxiv.org/pdf/1804.08266v1.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":"nlitrans-at-semeval-2018-task-12-transfer-of","repo_url":"https://github.com/IKMLab/arct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Position"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"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}