{"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/deep-enhanced-representation-for-implicit","title":"Deep Enhanced Representation for Implicit Discourse Relation Recognition","arxiv_id":"1807.05154","date":"2018-07-13","proceeding":"COLING 2018 8","authors":["Hongxiao Bai","Hai Zhao"],"abstract":"Implicit discourse relation recognition is a challenging task as the relation\nprediction without explicit connectives in discourse parsing needs\nunderstanding of text spans and cannot be easily derived from surface features\nfrom the input sentence pairs. Thus, properly representing the text is very\ncrucial to this task. In this paper, we propose a model augmented with\ndifferent grained text representations, including character, subword, word,\nsentence, and sentence pair levels. The proposed deeper model is evaluated on\nthe benchmark treebank and achieves state-of-the-art accuracy with greater than\n48% in 11-way and $F_1$ score greater than 50% in 4-way classifications for the\nfirst time according to our best knowledge.","url_abs":"http://arxiv.org/abs/1807.05154v1","url_pdf":"http://arxiv.org/pdf/1807.05154v1.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":"deep-enhanced-representation-for-implicit","repo_url":"https://github.com/diccooo/Deep_Enhanced_Repr_for_IDRR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.05154","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}