{"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/no-training-required-exploring-random","title":"No Training Required: Exploring Random Encoders for Sentence Classification","arxiv_id":"1901.10444","date":"2019-01-29","proceeding":"ICLR 2019 5","authors":["John Wieting","Douwe Kiela"],"abstract":"We explore various methods for computing sentence representations from\npre-trained word embeddings without any training, i.e., using nothing but\nrandom parameterizations. Our aim is to put sentence embeddings on more solid\nfooting by 1) looking at how much modern sentence embeddings gain over random\nmethods---as it turns out, surprisingly little; and by 2) providing the field\nwith more appropriate baselines going forward---which are, as it turns out,\nquite strong. We also make important observations about proper experimental\nprotocol for sentence classification evaluation, together with recommendations\nfor future research.","url_abs":"http://arxiv.org/abs/1901.10444v1","url_pdf":"http://arxiv.org/pdf/1901.10444v1.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":"no-training-required-exploring-random","repo_url":"https://github.com/facebookresearch/randsent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.10444","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}