{"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/efficient-purely-convolutional-text-encoding","title":"Efficient Purely Convolutional Text Encoding","arxiv_id":"1808.01160","date":"2018-08-03","proceeding":null,"authors":["Szymon Malik","Adrian Lancucki","Jan Chorowski"],"abstract":"In this work, we focus on a lightweight convolutional architecture that\ncreates fixed-size vector embeddings of sentences. Such representations are\nuseful for building NLP systems, including conversational agents. Our work\nderives from a recently proposed recursive convolutional architecture for\nauto-encoding text paragraphs at byte level. We propose alternations that\nsignificantly reduce training time, the number of parameters, and improve\nauto-encoding accuracy. Finally, we evaluate the representations created by our\nmodel on tasks from SentEval benchmark suite, and show that it can serve as a\nbetter, yet fairly low-resource alternative to popular bag-of-words embeddings.","url_abs":"http://arxiv.org/abs/1808.01160v1","url_pdf":"http://arxiv.org/pdf/1808.01160v1.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":"efficient-purely-convolutional-text-encoding","repo_url":"https://github.com/smalik169/recursive-convolutional-autoencoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}