{"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-a-natural-language-interface-with","title":"Learning a Natural Language Interface with Neural Programmer","arxiv_id":"1611.08945","date":"2016-11-28","proceeding":null,"authors":["Arvind Neelakantan","Quoc V. Le","Martin Abadi","Andrew McCallum","Dario Amodei"],"abstract":"Learning a natural language interface for database tables is a challenging\ntask that involves deep language understanding and multi-step reasoning. The\ntask is often approached by mapping natural language queries to logical forms\nor programs that provide the desired response when executed on the database. To\nour knowledge, this paper presents the first weakly supervised, end-to-end\nneural network model to induce such programs on a real-world dataset. We\nenhance the objective function of Neural Programmer, a neural network with\nbuilt-in discrete operations, and apply it on WikiTableQuestions, a natural\nlanguage question-answering dataset. The model is trained end-to-end with weak\nsupervision of question-answer pairs, and does not require domain-specific\ngrammars, rules, or annotations that are key elements in previous approaches to\nprogram induction. The main experimental result in this paper is that a single\nNeural Programmer model achieves 34.2% accuracy using only 10,000 examples with\nweak supervision. An ensemble of 15 models, with a trivial combination\ntechnique, achieves 37.7% accuracy, which is competitive to the current\nstate-of-the-art accuracy of 37.1% obtained by a traditional natural language\nsemantic parser.","url_abs":"http://arxiv.org/abs/1611.08945v4","url_pdf":"http://arxiv.org/pdf/1611.08945v4.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-a-natural-language-interface-with","repo_url":"https://github.com/tensorflow/models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"learning-a-natural-language-interface-with","repo_url":"https://github.com/pramodkaushik/np_analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"program-induction","task_name":"Program induction"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08945","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}