{"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/simple-and-effective-dimensionality-reduction","title":"Simple and Effective Dimensionality Reduction for Word Embeddings","arxiv_id":"1708.03629","date":"2017-08-11","proceeding":null,"authors":["Vikas Raunak"],"abstract":"Word embeddings have become the basic building blocks for several natural\nlanguage processing and information retrieval tasks. Pre-trained word\nembeddings are used in several downstream applications as well as for\nconstructing representations for sentences, paragraphs and documents. Recently,\nthere has been an emphasis on further improving the pre-trained word vectors\nthrough post-processing algorithms. One such area of improvement is the\ndimensionality reduction of the word embeddings. Reducing the size of word\nembeddings through dimensionality reduction can improve their utility in memory\nconstrained devices, benefiting several real-world applications. In this work,\nwe present a novel algorithm that effectively combines PCA based dimensionality\nreduction with a recently proposed post-processing algorithm, to construct word\nembeddings of lower dimensions. Empirical evaluations on 12 standard word\nsimilarity benchmarks show that our algorithm reduces the embedding\ndimensionality by 50%, while achieving similar or (more often) better\nperformance than the higher dimension embeddings.","url_abs":"http://arxiv.org/abs/1708.03629v3","url_pdf":"http://arxiv.org/pdf/1708.03629v3.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":"simple-and-effective-dimensionality-reduction","repo_url":"https://github.com/vyraun/Half-Size","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.03629","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}