{"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/fully-character-level-neural-machine","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","arxiv_id":"1610.03017","date":"2016-10-10","proceeding":"TACL 2017 1","authors":["Jason Lee","Kyunghyun Cho","Thomas Hofmann"],"abstract":"Most existing machine translation systems operate at the level of words,\nrelying on explicit segmentation to extract tokens. We introduce a neural\nmachine translation (NMT) model that maps a source character sequence to a\ntarget character sequence without any segmentation. We employ a character-level\nconvolutional network with max-pooling at the encoder to reduce the length of\nsource representation, allowing the model to be trained at a speed comparable\nto subword-level models while capturing local regularities. Our\ncharacter-to-character model outperforms a recently proposed baseline with a\nsubword-level encoder on WMT'15 DE-EN and CS-EN, and gives comparable\nperformance on FI-EN and RU-EN. We then demonstrate that it is possible to\nshare a single character-level encoder across multiple languages by training a\nmodel on a many-to-one translation task. In this multilingual setting, the\ncharacter-level encoder significantly outperforms the subword-level encoder on\nall the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality\nof the multilingual character-level translation even surpasses the models\nspecifically trained on that language pair alone, both in terms of BLEU score\nand human judgment.","url_abs":"http://arxiv.org/abs/1610.03017v3","url_pdf":"http://arxiv.org/pdf/1610.03017v3.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":"fully-character-level-neural-machine","repo_url":"https://github.com/nyu-dl/dl4mt-c2c","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"fully-character-level-neural-machine","repo_url":"https://github.com/stefan-it/deep-eos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"de-en","task_name":"de-en"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.03017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.03017"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/stefan-it/deep-eos","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-dl/dl4mt-c2c","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"8569db484e9d39b6","entry":"itemlist","repo":"nyu-dl/dl4mt-c2c","repo_kind":"official","path":"bpe2char/mixer.py","file_url":"https://github.com/nyu-dl/dl4mt-c2c/blob/HEAD/bpe2char/mixer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8569db484e9d39b6"}},{"code_sha256_prefix":"171953963fb4d022","entry":"fopen","repo":"nyu-dl/dl4mt-c2c","repo_kind":"official","path":"bpe2char/data_iterator.py","file_url":"https://github.com/nyu-dl/dl4mt-c2c/blob/HEAD/bpe2char/data_iterator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"171953963fb4d022"}},{"code_sha256_prefix":"73d1b90c1f18304d","entry":"unzip","repo":"nyu-dl/dl4mt-c2c","repo_kind":"official","path":"bpe2char/mixer.py","file_url":"https://github.com/nyu-dl/dl4mt-c2c/blob/HEAD/bpe2char/mixer.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"73d1b90c1f18304d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}