{"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/textual-analogy-parsing-whats-shared-and","title":"Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts","arxiv_id":"1809.02700","date":"2018-09-07","proceeding":"EMNLP 2018 10","authors":["Matthew Lamm","Arun Tejasvi Chaganty","Christopher D. Manning","Dan Jurafsky","Percy Liang"],"abstract":"To understand a sentence like \"whereas only 10% of White Americans live at or\nbelow the poverty line, 28% of African Americans do\" it is important not only\nto identify individual facts, e.g., poverty rates of distinct demographic\ngroups, but also the higher-order relations between them, e.g., the disparity\nbetween them. In this paper, we propose the task of Textual Analogy Parsing\n(TAP) to model this higher-order meaning. The output of TAP is a frame-style\nmeaning representation which explicitly specifies what is shared (e.g., poverty\nrates) and what is compared (e.g., White Americans vs. African Americans, 10%\nvs. 28%) between its component facts. Such a meaning representation can enable\nnew applications that rely on discourse understanding such as automated chart\ngeneration from quantitative text. We present a new dataset for TAP, baselines,\nand a model that successfully uses an ILP to enforce the structural constraints\nof the problem.","url_abs":"http://arxiv.org/abs/1809.02700v1","url_pdf":"http://arxiv.org/pdf/1809.02700v1.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":"textual-analogy-parsing-whats-shared-and","repo_url":"https://github.com/mrlamm/textual-analogy-parsing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"textual-analogy-parsing-whats-shared-and","repo_url":"https://github.com/leduoyang/IRIE_project_2018_relation_extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"textual-analogy-parsing","task_name":"Textual Analogy Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.02700","atlas_url":"https://app.syntology.ai/?focus=1809.02700","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}