{"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/deep-learning-for-joint-source-channel-coding","title":"Deep Learning for Joint Source-Channel Coding of Text","arxiv_id":"1802.06832","date":"2018-02-19","proceeding":null,"authors":["Nariman Farsad","Milind Rao","Andrea Goldsmith"],"abstract":"We consider the problem of joint source and channel coding of structured data\nsuch as natural language over a noisy channel. The typical approach to this\nproblem in both theory and practice involves performing source coding to first\ncompress the text and then channel coding to add robustness for the\ntransmission across the channel. This approach is optimal in terms of\nminimizing end-to-end distortion with arbitrarily large block lengths of both\nthe source and channel codes when transmission is over discrete memoryless\nchannels. However, the optimality of this approach is no longer ensured for\ndocuments of finite length and limitations on the length of the encoding. We\nwill show in this scenario that we can achieve lower word error rates by\ndeveloping a deep learning based encoder and decoder. While the approach of\nseparate source and channel coding would minimize bit error rates, our approach\npreserves semantic information of sentences by first embedding sentences in a\nsemantic space where sentences closer in meaning are located closer together,\nand then performing joint source and channel coding on these embeddings.","url_abs":"http://arxiv.org/abs/1802.06832v1","url_pdf":"http://arxiv.org/pdf/1802.06832v1.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":"deep-learning-for-joint-source-channel-coding","repo_url":"https://github.com/milindmrao/nlp_comm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}