{"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/many-to-english-machine-translation-tools","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","arxiv_id":"2104.00290","date":"2021-04-01","proceeding":"ACL 2021 5","authors":["Thamme Gowda","Zhao Zhang","Chris A Mattmann","Jonathan May"],"abstract":"While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTData, NLCodec, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usable as a service, or as a parent model for transfer-learning to even lower-resource languages.","url_abs":"https://arxiv.org/abs/2104.00290v2","url_pdf":"https://arxiv.org/pdf/2104.00290v2.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":"many-to-english-machine-translation-tools","repo_url":"https://github.com/isi-nlp/nlcodec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"many-to-english-machine-translation-tools","repo_url":"https://github.com/thammegowda/006-many-to-eng","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":null,"method_name":null}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.00290","atlas_url":"https://app.syntology.ai/?focus=2104.00290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00290"}},"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":"deterministic:regex_extraction","url":"https://github.com/glample/fastBPE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/thammegowda/mtdata","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/isi-nlp/nlcodec","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"found_in_text":{"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":0,"samples":[{"code_sha256_prefix":"e54b92783a8ddbc7","entry":"best_dtype","repo":"isi-nlp/nlcodec","repo_kind":"official","path":"nlcodec/db/core.py","file_url":"https://github.com/isi-nlp/nlcodec/blob/HEAD/nlcodec/db/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e54b92783a8ddbc7"}},{"code_sha256_prefix":"280ccbb1b0e4fbd4","entry":"detect_extension","repo":"thammegowda/mtdata","repo_kind":"found_in_text","path":"mtdata/parser.py","file_url":"https://github.com/thammegowda/mtdata/blob/HEAD/mtdata/parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"280ccbb1b0e4fbd4"}},{"code_sha256_prefix":"f99e72c2983a154b","entry":"part_path_pads","repo":"isi-nlp/nlcodec","repo_kind":"official","path":"nlcodec/db/core.py","file_url":"https://github.com/isi-nlp/nlcodec/blob/HEAD/nlcodec/db/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f99e72c2983a154b"}},{"code_sha256_prefix":"c6cdc9376ddcef6a","entry":"clean","repo":"thammegowda/mtdata","repo_kind":"found_in_text","path":"mtdata/sgm.py","file_url":"https://github.com/thammegowda/mtdata/blob/HEAD/mtdata/sgm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6cdc9376ddcef6a"}},{"code_sha256_prefix":"b6e62eee451f9729","entry":"make_n_grams","repo":"isi-nlp/nlcodec","repo_kind":"official","path":"nlcodec/utils.py","file_url":"https://github.com/isi-nlp/nlcodec/blob/HEAD/nlcodec/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6e62eee451f9729"}},{"code_sha256_prefix":"ed8430505d05f010","entry":"right_replace","repo":"thammegowda/mtdata","repo_kind":"found_in_text","path":"mtdata/cache.py","file_url":"https://github.com/thammegowda/mtdata/blob/HEAD/mtdata/cache.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed8430505d05f010"}},{"code_sha256_prefix":"ed598e786b62e136","entry":"rreplace","repo":"thammegowda/mtdata","repo_kind":"found_in_text","path":"mtdata/data.py","file_url":"https://github.com/thammegowda/mtdata/blob/HEAD/mtdata/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed598e786b62e136"}},{"code_sha256_prefix":"391870b445058aab","entry":"subsequent_mask","repo":"isi-nlp/nlcodec","repo_kind":"official","path":"nlcodec/db/batch.py","file_url":"https://github.com/isi-nlp/nlcodec/blob/HEAD/nlcodec/db/batch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"391870b445058aab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}