{"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/be-concise-and-precise-synthesizing-open","title":"Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts","arxiv_id":"1904.07391","date":"2019-04-16","proceeding":null,"authors":["Rajarshi Bhowmik","Gerard de Melo"],"abstract":"Despite being vast repositories of factual information, cross-domain\nknowledge graphs, such as Wikidata and the Google Knowledge Graph, only\nsparsely provide short synoptic descriptions for entities. Such descriptions\nthat briefly identify the most discernible features of an entity provide\nreaders with a near-instantaneous understanding of what kind of entity they are\nbeing presented. They can also aid in tasks such as named entity\ndisambiguation, ontological type determination, and answering entity queries.\nGiven the rapidly increasing numbers of entities in knowledge graphs, a fully\nautomated synthesis of succinct textual descriptions from underlying factual\ninformation is essential. To this end, we propose a novel fact-to-sequence\nencoder-decoder model with a suitable copy mechanism to generate concise and\nprecise textual descriptions of entities. In an in-depth evaluation, we\ndemonstrate that our method significantly outperforms state-of-the-art\nalternatives.","url_abs":"http://arxiv.org/abs/1904.07391v1","url_pdf":"http://arxiv.org/pdf/1904.07391v1.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":"be-concise-and-precise-synthesizing-open","repo_url":"https://github.com/kingsaint/Wikidata-Descriptions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}