{"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/rst-discourse-parsing-with-second-stage-edu","title":"RST Discourse Parsing with Second-Stage EDU-Level Pre-training","arxiv_id":null,"date":"2022-05-01","proceeding":"ACL 2022 5","authors":["Nan Yu","Meishan Zhang","Guohong Fu","Min Zhang"],"abstract":"Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing.Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU).To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models.Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP).We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation.Experimental results on a benckmark dataset show that our method is highly effective,leading a 2.1-point improvement in F1-score.All codes and pre-trained models will be released publicly to facilitate future studies.","url_abs":"https://aclanthology.org/2022.acl-long.294","url_pdf":"https://aclanthology.org/2022.acl-long.294.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":"rst-discourse-parsing-with-second-stage-edu","repo_url":"https://github.com/yunan4nlp/e-nnrstparser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"discourse-marker-prediction","task_name":"Discourse Marker Prediction"},{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"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}