{"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/data-recombination-for-neural-semantic","title":"Data Recombination for Neural Semantic Parsing","arxiv_id":"1606.03622","date":"2016-06-11","proceeding":"ACL 2016 8","authors":["Robin Jia","Percy Liang"],"abstract":"Modeling crisp logical regularities is crucial in semantic parsing, making it\ndifficult for neural models with no task-specific prior knowledge to achieve\ngood results. In this paper, we introduce data recombination, a novel framework\nfor injecting such prior knowledge into a model. From the training data, we\ninduce a high-precision synchronous context-free grammar, which captures\nimportant conditional independence properties commonly found in semantic\nparsing. We then train a sequence-to-sequence recurrent network (RNN) model\nwith a novel attention-based copying mechanism on datapoints sampled from this\ngrammar, thereby teaching the model about these structural properties. Data\nrecombination improves the accuracy of our RNN model on three semantic parsing\ndatasets, leading to new state-of-the-art performance on the standard GeoQuery\ndataset for models with comparable supervision.","url_abs":"http://arxiv.org/abs/1606.03622v1","url_pdf":"http://arxiv.org/pdf/1606.03622v1.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":"data-recombination-for-neural-semantic","repo_url":"https://worksheets.codalab.org/worksheets/0x50757a37779b485f89012e4ba03b6f4f","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.03622","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}