{"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/end-to-end-non-autoregressive-neural-machine","title":"End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification","arxiv_id":"1811.04719","date":"2018-11-12","proceeding":null,"authors":["Jindřich Libovický","Jindřich Helcl"],"abstract":"Autoregressive decoding is the only part of sequence-to-sequence models that\nprevents them from massive parallelization at inference time.\nNon-autoregressive models enable the decoder to generate all output symbols\nindependently in parallel. We present a novel non-autoregressive architecture\nbased on connectionist temporal classification and evaluate it on the task of\nneural machine translation. Unlike other non-autoregressive methods which\noperate in several steps, our model can be trained end-to-end. We conduct\nexperiments on the WMT English-Romanian and English-German datasets. Our models\nachieve a significant speedup over the autoregressive models, keeping the\ntranslation quality comparable to other non-autoregressive models.","url_abs":"http://arxiv.org/abs/1811.04719v1","url_pdf":"http://arxiv.org/pdf/1811.04719v1.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":"end-to-end-non-autoregressive-neural-machine","repo_url":"https://github.com/m3yrin/nar-latent-alignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.04719","atlas_url":"https://app.syntology.ai/?focus=1811.04719","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}