{"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/document-classification-by-inversion-of","title":"Document Classification by Inversion of Distributed Language Representations","arxiv_id":"1504.07295","date":"2015-04-27","proceeding":"IJCNLP 2015 7","authors":["Matt Taddy"],"abstract":"There have been many recent advances in the structure and measurement of\ndistributed language models: those that map from words to a vector-space that\nis rich in information about word choice and composition. This vector-space is\nthe distributed language representation. The goal of this note is to point out\nthat any distributed representation can be turned into a classifier through\ninversion via Bayes rule. The approach is simple and modular, in that it will\nwork with any language representation whose training can be formulated as\noptimizing a probability model. In our application to 2 million sentences from\nYelp reviews, we also find that it performs as well as or better than complex\npurpose-built algorithms.","url_abs":"http://arxiv.org/abs/1504.07295v3","url_pdf":"http://arxiv.org/pdf/1504.07295v3.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":"document-classification-by-inversion-of","repo_url":"https://github.com/taddylab/deepir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.07295","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}