{"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/the-ebible-corpus-data-and-model-benchmarks","title":"The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages","arxiv_id":"2304.09919","date":"2023-04-19","proceeding":null,"authors":["Vesa Akerman","David Baines","Damien Daspit","Ulf Hermjakob","Taeho Jang","Colin Leong","Michael Martin","Joel Mathew","Jonathan Robie","Marcus Schwarting"],"abstract":"Efficiently and accurately translating a corpus into a low-resource language remains a challenge, regardless of the strategies employed, whether manual, automated, or a combination of the two. Many Christian organizations are dedicated to the task of translating the Holy Bible into languages that lack a modern translation. Bible translation (BT) work is currently underway for over 3000 extremely low resource languages. We introduce the eBible corpus: a dataset containing 1009 translations of portions of the Bible with data in 833 different languages across 75 language families. In addition to a BT benchmarking dataset, we introduce model performance benchmarks built on the No Language Left Behind (NLLB) neural machine translation (NMT) models. Finally, we describe several problems specific to the domain of BT and consider how the established data and model benchmarks might be used for future translation efforts. For a BT task trained with NLLB, Austronesian and Trans-New Guinea language families achieve 35.1 and 31.6 BLEU scores respectively, which spurs future innovations for NMT for low-resource languages in Papua New Guinea.","url_abs":"https://arxiv.org/abs/2304.09919v1","url_pdf":"https://arxiv.org/pdf/2304.09919v1.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":"the-ebible-corpus-data-and-model-benchmarks","repo_url":"https://github.com/biblenlp/ebible-experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2304.09919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09919"}},"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/biblenlp/ebible-experiments","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"ran":0,"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":"9c4db71c0c8da03b","entry":"calculate_bleu_score","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/bleu.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/bleu.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":true,"mcp_get_code":{"code_sha256":"9c4db71c0c8da03b"}},{"code_sha256_prefix":"f39377668c0338f8","entry":"choose_yes_no","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/copy_selected.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/copy_selected.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":true,"mcp_get_code":{"code_sha256":"f39377668c0338f8"}},{"code_sha256_prefix":"97bbcc3931d0b2cc","entry":"choose_yes_no","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/modify_configs.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/modify_configs.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":true,"mcp_get_code":{"code_sha256":"97bbcc3931d0b2cc"}},{"code_sha256_prefix":"af1329ad61fa212e","entry":"count_lines","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_bybook.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_bybook.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":true,"mcp_get_code":{"code_sha256":"af1329ad61fa212e"}},{"code_sha256_prefix":"ff61d86aa37e442b","entry":"find_first_in_file","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_overall.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_overall.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":true,"mcp_get_code":{"code_sha256":"ff61d86aa37e442b"}},{"code_sha256_prefix":"6c994c446d928a9c","entry":"find_last_in_file","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_overall.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_overall.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":true,"mcp_get_code":{"code_sha256":"6c994c446d928a9c"}},{"code_sha256_prefix":"5ae9f90e9e2ffc87","entry":"get_config_data","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_bybook.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_bybook.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":true,"mcp_get_code":{"code_sha256":"5ae9f90e9e2ffc87"}},{"code_sha256_prefix":"7b0424e3118fe3c3","entry":"get_dest_file","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/copy_experiments.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/copy_experiments.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":true,"mcp_get_code":{"code_sha256":"7b0424e3118fe3c3"}},{"code_sha256_prefix":"f46c2741fea7a9a0","entry":"get_set_sizes","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_bybook.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_bybook.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":true,"mcp_get_code":{"code_sha256":"f46c2741fea7a9a0"}},{"code_sha256_prefix":"3eb88f5938ed0684","entry":"helper_function","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/summarize_scores_overall.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/summarize_scores_overall.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":true,"mcp_get_code":{"code_sha256":"3eb88f5938ed0684"}},{"code_sha256_prefix":"cd9da2ff4f9d8f61","entry":"is_excluded","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/copy_experiments.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/copy_experiments.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":true,"mcp_get_code":{"code_sha256":"cd9da2ff4f9d8f61"}},{"code_sha256_prefix":"03d5b3de4b57f059","entry":"is_included","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/make_configs.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/make_configs.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":true,"mcp_get_code":{"code_sha256":"03d5b3de4b57f059"}},{"code_sha256_prefix":"cb80bdf225558f82","entry":"load_tokenized_file","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/bleu.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/bleu.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":true,"mcp_get_code":{"code_sha256":"cb80bdf225558f82"}},{"code_sha256_prefix":"563364e92a40d4da","entry":"modify_config","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/modify_configs.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/modify_configs.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":true,"mcp_get_code":{"code_sha256":"563364e92a40d4da"}},{"code_sha256_prefix":"d89f199f63ea440b","entry":"read_and_tokenize_file","repo":"biblenlp/ebible-experiments","repo_kind":"official","path":"code/python/bleu.py","file_url":"https://github.com/biblenlp/ebible-experiments/blob/HEAD/code/python/bleu.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":true,"mcp_get_code":{"code_sha256":"d89f199f63ea440b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}