{"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/post-processing-of-word-representations-via","title":"Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding","arxiv_id":"1808.06305","date":"2018-08-20","proceeding":null,"authors":["Bin Wang","Fenxiao Chen","Angela Wang","C. -C. Jay Kuo"],"abstract":"Although embedded vector representations of words offer impressive\nperformance on many natural language processing (NLP) applications, the\ninformation of ordered input sequences is lost to some extent if only\ncontext-based samples are used in the training. For further performance\nimprovement, two new post-processing techniques, called post-processing via\nvariance normalization (PVN) and post-processing via dynamic embedding (PDE),\nare proposed in this work. The PVN method normalizes the variance of principal\ncomponents of word vectors while the PDE method learns orthogonal latent\nvariables from ordered input sequences. The PVN and the PDE methods can be\nintegrated to achieve better performance. We apply these post-processing\ntechniques to two popular word embedding methods (i.e., word2vec and GloVe) to\nyield their post-processed representations. Extensive experiments are conducted\nto demonstrate the effectiveness of the proposed post-processing techniques.","url_abs":"http://arxiv.org/abs/1808.06305v3","url_pdf":"http://arxiv.org/pdf/1808.06305v3.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":"post-processing-of-word-representations-via","repo_url":"https://github.com/BinWang28/PVN-Post-Processing-of-word-representation-via-variance-normalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.06305","atlas_url":"https://app.syntology.ai/?focus=1808.06305","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}