{"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-literature-study-of-embeddings-on-source","title":"A Literature Study of Embeddings on Source Code","arxiv_id":"1904.03061","date":"2019-04-05","proceeding":null,"authors":["Zimin Chen","Martin Monperrus"],"abstract":"Natural language processing has improved tremendously after the success of\nword embedding techniques such as word2vec. Recently, the same idea has been\napplied on source code with encouraging results. In this survey, we aim to\ncollect and discuss the usage of word embedding techniques on programs and\nsource code. The articles in this survey have been collected by asking authors\nof related work and with an extensive search on Google Scholar. Each article is\ncategorized into five categories: 1. embedding of tokens 2. embedding of\nfunctions or methods 3. embedding of sequences or sets of method calls 4.\nembedding of binary code 5. other embeddings. We also provide links to\nexperimental data and show some remarkable visualization of code embeddings. In\nsummary, word embedding has been successfully applied on different\ngranularities of source code. With access to countless open-source\nrepositories, we see a great potential of applying other data-driven natural\nlanguage processing techniques on source code in the future.","url_abs":"http://arxiv.org/abs/1904.03061v1","url_pdf":"http://arxiv.org/pdf/1904.03061v1.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-literature-study-of-embeddings-on-source","repo_url":"https://github.com/boyter/cs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}