{"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/robust-open-vocabulary-translation-from","title":"Robust Open-Vocabulary Translation from Visual Text Representations","arxiv_id":"2104.08211","date":"2021-04-16","proceeding":"EMNLP 2021 11","authors":["Elizabeth Salesky","David Etter","Matt Post"],"abstract":"Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models susceptible to degradation from common types of noise and variation. Motivated by the robustness of human language processing, we propose the use of visual text representations, which dispense with a finite set of text embeddings in favor of continuous vocabularies created by processing visually rendered text with sliding windows. We show that models using visual text representations approach or match performance of traditional text models on small and larger datasets. More importantly, models with visual embeddings demonstrate significant robustness to varied types of noise, achieving e.g., 25.9 BLEU on a character permuted German-English task where subword models degrade to 1.9.","url_abs":"https://arxiv.org/abs/2104.08211v3","url_pdf":"https://arxiv.org/pdf/2104.08211v3.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":"robust-open-vocabulary-translation-from","repo_url":"https://github.com/esalesky/visrep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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/2104.08211","atlas_url":"https://app.syntology.ai/?focus=2104.08211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08211"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/esalesky/visrep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"esalesky/visrep","repo_kind":"official","path":"fairseq/binarizer.py","file_url":"https://github.com/esalesky/visrep/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"b17acca882c5fdae","entry":"edit_distance","repo":"esalesky/visrep","repo_kind":"official","path":"text_utils.py","file_url":"https://github.com/esalesky/visrep/blob/HEAD/text_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b17acca882c5fdae"}},{"code_sha256_prefix":"c29acb0d4919d499","entry":"utf8_to_uxxxx","repo":"esalesky/visrep","repo_kind":"official","path":"text_utils.py","file_url":"https://github.com/esalesky/visrep/blob/HEAD/text_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c29acb0d4919d499"}},{"code_sha256_prefix":"f186bd86fca49ce9","entry":"uxxxx_to_utf8","repo":"esalesky/visrep","repo_kind":"official","path":"text_utils.py","file_url":"https://github.com/esalesky/visrep/blob/HEAD/text_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f186bd86fca49ce9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}