{"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/learning-to-generate-one-sentence-biographies","title":"Learning to generate one-sentence biographies from Wikidata","arxiv_id":"1702.06235","date":"2017-02-21","proceeding":"EACL 2017 4","authors":["Andrew Chisholm","Will Radford","Ben Hachey"],"abstract":"We investigate the generation of one-sentence Wikipedia biographies from\nfacts derived from Wikidata slot-value pairs. We train a recurrent neural\nnetwork sequence-to-sequence model with attention to select facts and generate\ntextual summaries. Our model incorporates a novel secondary objective that\nhelps ensure it generates sentences that contain the input facts. The model\nachieves a BLEU score of 41, improving significantly upon the vanilla\nsequence-to-sequence model and scoring roughly twice that of a simple template\nbaseline. Human preference evaluation suggests the model is nearly as good as\nthe Wikipedia reference. Manual analysis explores content selection, suggesting\nthe model can trade the ability to infer knowledge against the risk of\nhallucinating incorrect information.","url_abs":"http://arxiv.org/abs/1702.06235v1","url_pdf":"http://arxiv.org/pdf/1702.06235v1.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":"learning-to-generate-one-sentence-biographies","repo_url":"https://github.com/andychisholm/mimo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.06235","atlas_url":"https://app.syntology.ai/?focus=1702.06235","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}