{"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/gdtb-genre-diverse-data-for-english-shallow","title":"GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains","arxiv_id":"2411.00491","date":"2024-11-01","proceeding":null,"authors":["Yang Janet Liu","Tatsuya Aoyama","Wesley Scivetti","YIlun Zhu","Shabnam Behzad","Lauren Elizabeth Levine","Jessica Lin","Devika Tiwari","Amir Zeldes"],"abstract":"Work on shallow discourse parsing in English has focused on the Wall Street Journal corpus, the only large-scale dataset for the language in the PDTB framework. However, the data is not openly available, is restricted to the news domain, and is by now 35 years old. In this paper, we present and evaluate a new open-access, multi-genre benchmark for PDTB-style shallow discourse parsing, based on the existing UD English GUM corpus, for which discourse relation annotations in other frameworks already exist. In a series of experiments on cross-domain relation classification, we show that while our dataset is compatible with PDTB, substantial out-of-domain degradation is observed, which can be alleviated by joint training on both datasets.","url_abs":"https://arxiv.org/abs/2411.00491v1","url_pdf":"https://arxiv.org/pdf/2411.00491v1.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":"gdtb-genre-diverse-data-for-english-shallow","repo_url":"https://github.com/gucorpling/gum2pdtb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.00491","atlas_url":"https://app.syntology.ai/?focus=2411.00491","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}