{"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/a-stochastic-decoder-for-neural-machine","title":"A Stochastic Decoder for Neural Machine Translation","arxiv_id":"1805.10844","date":"2018-05-28","proceeding":"ACL 2018 7","authors":["Philip Schulz","Wilker Aziz","Trevor Cohn"],"abstract":"The process of translation is ambiguous, in that there are typically many\nvalid trans- lations for a given sentence. This gives rise to significant\nvariation in parallel cor- pora, however, most current models of machine\ntranslation do not account for this variation, instead treating the prob- lem\nas a deterministic process. To this end, we present a deep generative model of\nmachine translation which incorporates a chain of latent variables, in order to\nac- count for local lexical and syntactic varia- tion in parallel corpora. We\nprovide an in- depth analysis of the pitfalls encountered in variational\ninference for training deep generative models. Experiments on sev- eral\ndifferent language pairs demonstrate that the model consistently improves over\nstrong baselines.","url_abs":"http://arxiv.org/abs/1805.10844v1","url_pdf":"http://arxiv.org/pdf/1805.10844v1.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":"a-stochastic-decoder-for-neural-machine","repo_url":"https://github.com/awslabs/sockeye","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}