{"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/neural-rst-based-evaluation-of-discourse","title":"Neural RST-based Evaluation of Discourse Coherence","arxiv_id":"2009.14463","date":"2020-09-30","proceeding":"Asian Chapter of the Association for Computational Linguistics 2020","authors":["Grigorii Guz","Peyman Bateni","Darius Muglich","Giuseppe Carenini"],"abstract":"This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We demonstrate this through our tree-recursive neural model, namely RST-Recursive, which takes advantage of the text's RST features produced by a state of the art RST parser. We evaluate our approach on the Grammarly Corpus for Discourse Coherence (GCDC) and show that when ensembled with the current state of the art, we can achieve the new state of the art accuracy on this benchmark. Furthermore, when deployed alone, RST-Recursive achieves competitive accuracy while having 62% fewer parameters.","url_abs":"https://arxiv.org/abs/2009.14463v1","url_pdf":"https://arxiv.org/pdf/2009.14463v1.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":"neural-rst-based-evaluation-of-discourse","repo_url":"https://github.com/grig-guz/coherence-rst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"coherence-evaluation","task_name":"Coherence Evaluation"},{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-accuracy","task":"Coherence Evaluation","dataset":"GCDC + RST - Accuracy","model":"RST-Ensemble","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"55.39"},"uses_additional_data":false},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-accuracy","task":"Coherence Evaluation","dataset":"GCDC + RST - Accuracy","model":"RST-Recursive","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"53.04"},"uses_additional_data":false},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-f1","task":"Coherence Evaluation","dataset":"GCDC + RST - F1","model":"RST-Ensemble","rank_in_archive_order":1,"of":3,"metrics":{"Average F1":"46.98"},"uses_additional_data":false},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-f1","task":"Coherence Evaluation","dataset":"GCDC + RST - F1","model":"RST-Recursive","rank_in_archive_order":3,"of":3,"metrics":{"Average F1":"44.30"},"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}