{"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/dynamic-bernoulli-embeddings-for-language","title":"Dynamic Bernoulli Embeddings for Language Evolution","arxiv_id":"1703.08052","date":"2017-03-23","proceeding":null,"authors":["Maja Rudolph","David Blei"],"abstract":"Word embeddings are a powerful approach for unsupervised analysis of\nlanguage. Recently, Rudolph et al. (2016) developed exponential family\nembeddings, which cast word embeddings in a probabilistic framework. Here, we\ndevelop dynamic embeddings, building on exponential family embeddings to\ncapture how the meanings of words change over time. We use dynamic embeddings\nto analyze three large collections of historical texts: the U.S. Senate\nspeeches from 1858 to 2009, the history of computer science ACM abstracts from\n1951 to 2014, and machine learning papers on the Arxiv from 2007 to 2015. We\nfind dynamic embeddings provide better fits than classical embeddings and\ncapture interesting patterns about how language changes.","url_abs":"http://arxiv.org/abs/1703.08052v1","url_pdf":"http://arxiv.org/pdf/1703.08052v1.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":"dynamic-bernoulli-embeddings-for-language","repo_url":"https://github.com/mariru/dynamic_bernoulli_embeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}