{"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/how-much-is-131-million-dollars-putting","title":"How Much is 131 Million Dollars? Putting Numbers in Perspective with Compositional Descriptions","arxiv_id":"1609.00070","date":"2016-09-01","proceeding":"ACL 2016 8","authors":["Arun Tejasvi Chaganty","Percy Liang"],"abstract":"How much is 131 million US dollars? To help readers put such numbers in\ncontext, we propose a new task of automatically generating short descriptions\nknown as perspectives, e.g. \"$131 million is about the cost to employ everyone\nin Texas over a lunch period\". First, we collect a dataset of numeric mentions\nin news articles, where each mention is labeled with a set of rated\nperspectives. We then propose a system to generate these descriptions\nconsisting of two steps: formula construction and description generation. In\nconstruction, we compose formulae from numeric facts in a knowledge base and\nrank the resulting formulas based on familiarity, numeric proximity and\nsemantic compatibility. In generation, we convert a formula into natural\nlanguage using a sequence-to-sequence recurrent neural network. Our system\nobtains a 15.2% F1 improvement over a non-compositional baseline at formula\nconstruction and a 12.5 BLEU point improvement over a baseline description\ngeneration.","url_abs":"http://arxiv.org/abs/1609.00070v1","url_pdf":"http://arxiv.org/pdf/1609.00070v1.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":"how-much-is-131-million-dollars-putting","repo_url":"https://worksheets.codalab.org/worksheets/0x243284b4d81d4590b46030cdd3b72633","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.00070","atlas_url":"https://app.syntology.ai/?focus=1609.00070","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}