{"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/a-simple-and-strong-baseline-for-end-to-end","title":"A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing","arxiv_id":"2210.08355","date":"2022-10-15","proceeding":null,"authors":["Naoki Kobayashi","Tsutomu Hirao","Hidetaka Kamigaito","Manabu Okumura","Masaaki Nagata"],"abstract":"To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results. This paper explores a strong baseline by integrating existing simple parsing strategies, top-down and bottom-up, with various transformer-based pre-trained language models. The experimental results obtained from two benchmark datasets demonstrate that the parsing performance strongly relies on the pretrained language models rather than the parsing strategies. In particular, the bottom-up parser achieves large performance gains compared to the current best parser when employing DeBERTa. We further reveal that language models with a span-masking scheme especially boost the parsing performance through our analysis within intra- and multi-sentential parsing, and nuclearity prediction.","url_abs":"https://arxiv.org/abs/2210.08355v2","url_pdf":"https://arxiv.org/pdf/2210.08355v2.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":"a-simple-and-strong-baseline-for-end-to-end","repo_url":"https://github.com/nttcslab-nlp/rstparser_emnlp22","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"}],"methods":[{"method_slug":"deberta","method_name":"DeBERTa"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Bottom-up (DeBERTa)","rank_in_archive_order":1,"of":12,"metrics":{"Standard Parseval (Full)":"44.4","Standard Parseval (Nuclearity)":"60.0","Standard Parseval (Relation)":"51.4","Standard Parseval (Span)":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Top-down (DeBERTa)","rank_in_archive_order":2,"of":12,"metrics":{"Standard Parseval (Full)":"43.4","Standard Parseval (Nuclearity)":"57.9","Standard Parseval (Relation)":"50.0","Standard Parseval (Span)":"77.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Bottom-up (XLNet)","rank_in_archive_order":3,"of":12,"metrics":{"Standard Parseval (Full)":"40.7","Standard Parseval (Nuclearity)":"56.4","Standard Parseval (Relation)":"47.4","Standard Parseval (Span)":"73.6"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Top-down (RoBERTa)","rank_in_archive_order":4,"of":12,"metrics":{"Standard Parseval (Full)":"41.5","Standard Parseval (Nuclearity)":"56.1","Standard Parseval (Relation)":"48.7","Standard Parseval (Span)":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Bottom-up (RoBERTa)","rank_in_archive_order":5,"of":12,"metrics":{"Standard Parseval (Full)":"41.4","Standard Parseval (Nuclearity)":"55.5","Standard Parseval (Relation)":"47.9","Standard Parseval (Span)":"73.2"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Top-down (XLNet)","rank_in_archive_order":6,"of":12,"metrics":{"Standard Parseval (Full)":"40.2","Standard Parseval (Nuclearity)":"55.2","Standard Parseval (Relation)":"47.0","Standard Parseval (Span)":"74.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Top-down (SpanBERT)","rank_in_archive_order":7,"of":12,"metrics":{"Standard Parseval (Full)":"36.7","Standard Parseval (Nuclearity)":"54.5","Standard Parseval (Relation)":"42.7","Standard Parseval (Span)":"73.7"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Bottom-up (SpanBERT)","rank_in_archive_order":8,"of":12,"metrics":{"Standard Parseval (Full)":"40.5","Standard Parseval (Nuclearity)":"53.8","Standard Parseval (Relation)":"46.0","Standard Parseval (Span)":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Bottom-up (BERT)","rank_in_archive_order":10,"of":12,"metrics":{"Standard Parseval (Full)":"32.9","Standard Parseval (Nuclearity)":"46.3","Standard Parseval (Relation)":"39.5","Standard Parseval (Span)":"66.6"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-instructional-dt-instr","task":"Discourse Parsing","dataset":"Instructional-DT (Instr-DT)","model":"Top-down (BERT)","rank_in_archive_order":11,"of":12,"metrics":{"Standard Parseval (Full)":"30.9","Standard Parseval (Nuclearity)":"44.6","Standard Parseval (Relation)":"37.6","Standard Parseval (Span)":"65.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Bottom-up (DeBERTa)","rank_in_archive_order":7,"of":40,"metrics":{"Standard Parseval (Full)":"55.4 ± 0.4","Standard Parseval (Nuclearity)":"68.0 ± 0.5","Standard Parseval (Relation)":"57.3 ± 0.2","Standard Parseval (Span)":"77.8 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Top-down (XLNet)","rank_in_archive_order":8,"of":40,"metrics":{"Standard Parseval (Full)":"54.8","Standard Parseval (Nuclearity)":"67.4","Standard Parseval (Relation)":"57.0","Standard Parseval (Span)":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Top-down (DeBERTa)","rank_in_archive_order":9,"of":40,"metrics":{"Standard Parseval (Full)":"54.4","Standard Parseval (Nuclearity)":"67.9","Standard Parseval (Relation)":"56.6","Standard Parseval (Span)":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Bottom-up (XLNet)","rank_in_archive_order":10,"of":40,"metrics":{"Standard Parseval (Full)":"54.2","Standard Parseval (Nuclearity)":"65.9","Standard Parseval (Relation)":"56.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Top-down (RoBERTa)","rank_in_archive_order":11,"of":40,"metrics":{"Standard Parseval (Full)":"53.8","Standard Parseval (Nuclearity)":"66.6","Standard Parseval (Relation)":"55.8","Standard Parseval (Span)":"77.3"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Bottom-up (RoBERTa)","rank_in_archive_order":12,"of":40,"metrics":{"Standard Parseval (Full)":"53.7","Standard Parseval (Nuclearity)":"66.5","Standard Parseval (Relation)":"55.4","Standard Parseval (Span)":"76.1"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Bottom-up (SpanBERT)","rank_in_archive_order":14,"of":40,"metrics":{"Standard Parseval (Full)":"52.7","Standard Parseval (Nuclearity)":"65.3","Standard Parseval (Relation)":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Top-down (SpanBERT)","rank_in_archive_order":15,"of":40,"metrics":{"Standard Parseval (Full)":"52.2","Standard Parseval (Nuclearity)":"65.4","Standard Parseval (Relation)":"54.5","Standard Parseval (Span)":"76.5"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Top-down (BERT)","rank_in_archive_order":22,"of":40,"metrics":{"Standard Parseval (Full)":"46.6","Standard Parseval (Nuclearity)":"59.1","Standard Parseval (Relation)":"48.3","Standard Parseval (Span)":"69.8"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-parsing-on-rst-dt","task":"Discourse Parsing","dataset":"RST-DT","model":"Bottom-up (BERT)","rank_in_archive_order":23,"of":40,"metrics":{"Standard Parseval (Full)":"46.0","Standard Parseval (Nuclearity)":"57.8","Standard Parseval (Relation)":"47.8","Standard Parseval (Span)":"68.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}