{"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/visualizing-the-flow-of-discourse-with-a","title":"Visualizing the Flow of Discourse with a Concept Ontology","arxiv_id":"1802.08614","date":"2018-02-23","proceeding":null,"authors":["Baoxu Shi","Tim Weninger"],"abstract":"Understanding and visualizing human discourse has long being a challenging\ntask. Although recent work on argument mining have shown success in classifying\nthe role of various sentences, the task of recognizing concepts and\nunderstanding the ways in which they are discussed remains challenging. Given\nan email thread or a transcript of a group discussion, our task is to extract\nthe relevant concepts and understand how they are referenced and re-referenced\nthroughout the discussion. In the present work, we present a preliminary\napproach for extracting and visualizing group discourse by adapting Wikipedia's\ncategory hierarchy to be an external concept ontology. From a user study, we\nfound that our method achieved better results than 4 strong alternative\napproaches, and we illustrate our visualization method based on the extracted\ndiscourse flows.","url_abs":"http://arxiv.org/abs/1802.08614v1","url_pdf":"http://arxiv.org/pdf/1802.08614v1.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":"visualizing-the-flow-of-discourse-with-a","repo_url":"https://github.com/bxshi/DiscourseVisualization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"argument-mining","task_name":"Argument Mining"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}