{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/analyzing-uncertainty-in-neural-machine","title":"Analyzing Uncertainty in Neural Machine Translation","arxiv_id":"1803.00047","date":"2018-02-28","proceeding":"ICML 2018 7","authors":["Myle Ott","Michael Auli","David Grangier","Marc'Aurelio Ranzato"],"abstract":"Machine translation is a popular test bed for research in neural\nsequence-to-sequence models but despite much recent research, there is still a\nlack of understanding of these models. Practitioners report performance\ndegradation with large beams, the under-estimation of rare words and a lack of\ndiversity in the final translations. Our study relates some of these issues to\nthe inherent uncertainty of the task, due to the existence of multiple valid\ntranslations for a single source sentence, and to the extrinsic uncertainty\ncaused by noisy training data. We propose tools and metrics to assess how\nuncertainty in the data is captured by the model distribution and how it\naffects search strategies that generate translations. Our results show that\nsearch works remarkably well but that models tend to spread too much\nprobability mass over the hypothesis space. Next, we propose tools to assess\nmodel calibration and show how to easily fix some shortcomings of current\nmodels. As part of this study, we release multiple human reference translations\nfor two popular benchmarks.","url_abs":"http://arxiv.org/abs/1803.00047v4","url_pdf":"http://arxiv.org/pdf/1803.00047v4.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":"analyzing-uncertainty-in-neural-machine","repo_url":"https://github.com/facebookresearch/analyzing-uncertainty-nmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.00047","atlas_url":"https://app.syntology.ai/?focus=1803.00047","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1803.00047"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1803.00047\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1803.00047"},"call":"get_concepts_for_paper(arxiv_id=\"1803.00047\")"}],"by_repo":[{"repo":"facebookresearch/analyzing-uncertainty-nmt","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4a7c57a0cd9d36db3c1415ad16b43aeb754b90294ea62bd7b4d999dde74b3fce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}