{"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/unleashing-the-power-of-neural-discourse","title":"Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining","arxiv_id":"2011.03203","date":"2020-11-06","proceeding":null,"authors":["Grigorii Guz","Patrick Huber","Giuseppe Carenini"],"abstract":"RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale \"silver-standard\" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis.","url_abs":"https://arxiv.org/abs/2011.03203v1","url_pdf":"https://arxiv.org/pdf/2011.03203v1.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":[],"tasks":[{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"opinion-mining","task_name":"Opinion Mining"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Guz et al. (2020) (pretrained)","rank_in_archive_order":9,"of":12,"metrics":{"Standard Parseval (Nuclearity)":"46.59","Standard Parseval (Span)":"65.41"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Guz et al. (2020)","rank_in_archive_order":12,"of":12,"metrics":{"Standard Parseval (Nuclearity)":"44.41","Standard Parseval (Span)":"64.55"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Guz et al. (2020) (pretrained)","rank_in_archive_order":24,"of":40,"metrics":{"Standard Parseval (Nuclearity)":"61.86","Standard Parseval (Span)":"72.94"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Guz et al. (2020)","rank_in_archive_order":25,"of":40,"metrics":{"Standard Parseval (Nuclearity)":"61.38","Standard Parseval (Span)":"72.43"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2011.03203","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}