{"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/a-grammar-based-structural-cnn-decoder-for","title":"A Grammar-Based Structural CNN Decoder for Code Generation","arxiv_id":"1811.06837","date":"2018-11-14","proceeding":null,"authors":["Zeyu Sun","Qihao Zhu","Lili Mou","Yingfei Xiong","Ge Li","Lu Zhang"],"abstract":"Code generation maps a program description to executable source code in a\nprogramming language. Existing approaches mainly rely on a recurrent neural\nnetwork (RNN) as the decoder. However, we find that a program contains\nsignificantly more tokens than a natural language sentence, and thus it may be\ninappropriate for RNN to capture such a long sequence. In this paper, we\npropose a grammar-based structural convolutional neural network (CNN) for code\ngeneration. Our model generates a program by predicting the grammar rules of\nthe programming language; we design several CNN modules, including the\ntree-based convolution and pre-order convolution, whose information is further\naggregated by dedicated attentive pooling layers. Experimental results on the\nHearthStone benchmark dataset show that our CNN code generator significantly\noutperforms the previous state-of-the-art method by 5 percentage points;\nadditional experiments on several semantic parsing tasks demonstrate the\nrobustness of our model. We also conduct in-depth ablation test to better\nunderstand each component of our model.","url_abs":"http://arxiv.org/abs/1811.06837v1","url_pdf":"http://arxiv.org/pdf/1811.06837v1.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":"a-grammar-based-structural-cnn-decoder-for","repo_url":"https://github.com/zysszy/GrammarCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.06837","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}