{"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-word-embeddings-for-evolving-semantic","title":"Dynamic Word Embeddings for Evolving Semantic Discovery","arxiv_id":"1703.00607","date":"2017-03-02","proceeding":null,"authors":["Zijun Yao","Yifan Sun","Weicong Ding","Nikhil Rao","Hui Xiong"],"abstract":"Word evolution refers to the changing meanings and associations of words\nthroughout time, as a byproduct of human language evolution. By studying word\nevolution, we can infer social trends and language constructs over different\nperiods of human history. However, traditional techniques such as word\nrepresentation learning do not adequately capture the evolving language\nstructure and vocabulary. In this paper, we develop a dynamic statistical model\nto learn time-aware word vector representation. We propose a model that\nsimultaneously learns time-aware embeddings and solves the resulting \"alignment\nproblem\". This model is trained on a crawled NYTimes dataset. Additionally, we\ndevelop multiple intuitive evaluation strategies of temporal word embeddings.\nOur qualitative and quantitative tests indicate that our method not only\nreliably captures this evolution over time, but also consistently outperforms\nstate-of-the-art temporal embedding approaches on both semantic accuracy and\nalignment quality.","url_abs":"http://arxiv.org/abs/1703.00607v2","url_pdf":"http://arxiv.org/pdf/1703.00607v2.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-word-embeddings-for-evolving-semantic","repo_url":"https://github.com/lamantinushka/Time-dependent-embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"dynamic-word-embeddings-for-evolving-semantic","repo_url":"https://github.com/yifan0sun/DynamicWord2Vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00607","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}