{"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/character-level-question-answering-with","title":"Character-Level Question Answering with Attention","arxiv_id":"1604.00727","date":"2016-04-04","proceeding":"EMNLP 2016 11","authors":["David Golub","Xiaodong He"],"abstract":"We show that a character-level encoder-decoder framework can be successfully\napplied to question answering with a structured knowledge base. We use our\nmodel for single-relation question answering and demonstrate the effectiveness\nof our approach on the SimpleQuestions dataset (Bordes et al., 2015), where we\nimprove state-of-the-art accuracy from 63.9% to 70.9%, without use of\nensembles. Importantly, our character-level model has 16x fewer parameters than\nan equivalent word-level model, can be learned with significantly less data\ncompared to previous work, which relies on data augmentation, and is robust to\nnew entities in testing.","url_abs":"http://arxiv.org/abs/1604.00727v4","url_pdf":"http://arxiv.org/pdf/1604.00727v4.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":"character-level-question-answering-with","repo_url":"https://github.com/davidgolub/SimpleQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.00727","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}