{"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/rand-walk-a-latent-variable-model-approach-to","title":"A Latent Variable Model Approach to PMI-based Word Embeddings","arxiv_id":"1502.03520","date":"2015-02-12","proceeding":"TACL 2016 1","authors":["Sanjeev Arora","Yuanzhi Li","YIngyu Liang","Tengyu Ma","Andrej Risteski"],"abstract":"Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper proposes a new generative model, a dynamic version of the log-linear topic model of~\\citet{mnih2007three}. The methodological novelty is to use the prior to compute closed form expressions for word statistics. This provides a theoretical justification for nonlinear models like PMI, word2vec, and GloVe, as well as some hyperparameter choices. It also helps explain why low-dimensional semantic embeddings contain linear algebraic structure that allows solution of word analogies, as shown by~\\citet{mikolov2013efficient} and many subsequent papers. Experimental support is provided for the generative model assumptions, the most important of which is that latent word vectors are fairly uniformly dispersed in space.","url_abs":"https://arxiv.org/abs/1502.03520v8","url_pdf":"https://arxiv.org/pdf/1502.03520v8.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":"rand-walk-a-latent-variable-model-approach-to","repo_url":"https://github.com/PrincetonML/SemanticVector","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"rand-walk-a-latent-variable-model-approach-to","repo_url":"https://github.com/LivNLP/Relational-Walk-for-Knowledge-Graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"rand-walk-a-latent-variable-model-approach-to","repo_url":"https://github.com/tsandefer/capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"rand-walk-a-latent-variable-model-approach-to","repo_url":"https://github.com/tsandefer/dsi_capstone_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"glove","method_name":"GloVe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1502.03520","atlas_url":"https://app.syntology.ai/?focus=1502.03520","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}