{"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/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","arxiv_id":"1508.07909","date":"2015-08-31","proceeding":"ACL 2016 8","authors":["Rico Sennrich","Barry Haddow","Alexandra Birch"],"abstract":"Neural machine translation (NMT) models typically operate with a fixed\nvocabulary, but translation is an open-vocabulary problem. Previous work\naddresses the translation of out-of-vocabulary words by backing off to a\ndictionary. In this paper, we introduce a simpler and more effective approach,\nmaking the NMT model capable of open-vocabulary translation by encoding rare\nand unknown words as sequences of subword units. This is based on the intuition\nthat various word classes are translatable via smaller units than words, for\ninstance names (via character copying or transliteration), compounds (via\ncompositional translation), and cognates and loanwords (via phonological and\nmorphological transformations). We discuss the suitability of different word\nsegmentation techniques, including simple character n-gram models and a\nsegmentation based on the byte pair encoding compression algorithm, and\nempirically show that subword models improve over a back-off dictionary\nbaseline for the WMT 15 translation tasks English-German and English-Russian by\n1.1 and 1.3 BLEU, respectively.","url_abs":"http://arxiv.org/abs/1508.07909v5","url_pdf":"http://arxiv.org/pdf/1508.07909v5.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":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/rsennrich/subword-nmt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/Automattic/wp-translate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/Avmb/code-docstring-corpus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/EdinburghNLP/code-docstring-corpus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/HarshKhandelwal1552/Language_classifier_with_Naive_Bayes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/PaulSudarshan/Language-Classification-Using-Naive-Bayes-Algorithm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/SeonbeomKim/Python-Bype_Pair_Encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/ThAIKeras/bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/Xinsen-Zhang/transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/glample/fastBPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/johnr0/TaleBrush-backend","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/karpathy/minbpe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/kh-mo/QA_wikisql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/ksulima/Unsupervised-method-to-NPL-Polish-language","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/lkfo415579/MT-Readling-List","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/nyu-dl/dl4mt-c2c","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/nyu-dl/dl4mt-cdec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/nyu-dl/dl4mt-simul-trans","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/salesforce/GeDi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/simonjisu/NMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/siyuofzhou/CNNSeqToSeq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/thinkwee/DPP_CNN_Summarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/VKCOM/YouTokenToMe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-machine-translation-of-rare-words-with","repo_url":"https://github.com/google/sentencepiece","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"bpe","method_name":"BPE"}],"datasets_introduced":[],"methods_introduced":[{"slug":"bpe","name":"BPE","full_name":"Byte Pair Encoding"}],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2015-english-german","task":"Machine Translation","dataset":"WMT2015 English-German","model":"BPE word segmentation","rank_in_archive_order":4,"of":6,"metrics":{"BLEU score":"22.8"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2015-english","task":"Machine Translation","dataset":"WMT2015 English-Russian","model":"C2-50k Segmentation","rank_in_archive_order":1,"of":1,"metrics":{"BLEU score":"20.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1508.07909","atlas_url":"https://app.syntology.ai/?focus=1508.07909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.07909"}},"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/google/sentencepiece","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/fairseq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simonjisu/NMT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-dl/dl4mt-cdec","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EdinburghNLP/code-docstring-corpus","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SeonbeomKim/Python-Bype_Pair_Encoding","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaulSudarshan/Language-Classification-Using-Naive-Bayes-Algorithm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johnr0/TaleBrush-backend","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ksulima/Unsupervised-method-to-NPL-Polish-language","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VKCOM/YouTokenToMe","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siyuofzhou/CNNSeqToSeq","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/karpathy/minbpe","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-dl/dl4mt-c2c","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-dl/dl4mt-simul-trans","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rsennrich/subword-nmt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Automattic/wp-translate","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/GeDi","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Avmb/code-docstring-corpus","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/glample/fastBPE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kh-mo/QA_wikisql","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HarshKhandelwal1552/Language_classifier_with_Naive_Bayes","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Xinsen-Zhang/transformer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThAIKeras/bert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lkfo415579/MT-Readling-List","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":19,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"listed":{"samples":24,"ran":17,"repositories":6}},"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":21,"samples":[{"code_sha256_prefix":"33b1567b39f86e71","entry":"BPE","repo":"ThAIKeras/bert","repo_kind":"listed","path":"bpe_helper.py","file_url":"https://github.com/ThAIKeras/bert/blob/HEAD/bpe_helper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33b1567b39f86e71"}},{"code_sha256_prefix":"70a8fed9225c5845","entry":"_bpe2words","repo":"nyu-dl/dl4mt-simul-trans","repo_kind":"listed","path":"simultrans_model.py","file_url":"https://github.com/nyu-dl/dl4mt-simul-trans/blob/HEAD/simultrans_model.py","link_basis":"first_harvest_node","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":"70a8fed9225c5845"}},{"code_sha256_prefix":"2032a0c86da75680","entry":"check_merge_info","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2032a0c86da75680"}},{"code_sha256_prefix":"c837ac919bdfe91e","entry":"delete_some_stats","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c837ac919bdfe91e"}},{"code_sha256_prefix":"fe96394f96a9c638","entry":"get_pair_statistics","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fe96394f96a9c638"}},{"code_sha256_prefix":"e27a7ada9b96b37e","entry":"get_pair_statistics","repo":"kh-mo/QA_wikisql","repo_kind":"listed","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e27a7ada9b96b37e"}},{"code_sha256_prefix":"afdbbe2995c004e2","entry":"get_stats","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"afdbbe2995c004e2"}},{"code_sha256_prefix":"b83d785ca99bfc9f","entry":"get_vocabulary","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b83d785ca99bfc9f"}},{"code_sha256_prefix":"9425aef3e44f6979","entry":"get_vocabulary","repo":"kh-mo/QA_wikisql","repo_kind":"listed","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9425aef3e44f6979"}},{"code_sha256_prefix":"bc7574327ea1f634","entry":"get_vocabulary","repo":"thinkwee/DPP_CNN_Summarization","repo_kind":"listed","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc7574327ea1f634"}},{"code_sha256_prefix":"afac3ba7a001359e","entry":"get_vocabulary_from_learn_BPE","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"afac3ba7a001359e"}},{"code_sha256_prefix":"a4985508aef2cb2a","entry":"learn_bpe","repo":"kh-mo/QA_wikisql","repo_kind":"listed","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4985508aef2cb2a"}},{"code_sha256_prefix":"029694838a73e5fc","entry":"merge_bpe_word","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"029694838a73e5fc"}},{"code_sha256_prefix":"72ccea7ec0eb1e6a","entry":"merge_dictionary","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72ccea7ec0eb1e6a"}},{"code_sha256_prefix":"6aafe96a739d0b09","entry":"open_file","repo":"rsennrich/subword-nmt","repo_kind":"official","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/rsennrich/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6aafe96a739d0b09"}},{"code_sha256_prefix":"1c202c7e568439b5","entry":"render_token","repo":"karpathy/minbpe","repo_kind":"listed","path":"minbpe/base.py","file_url":"https://github.com/karpathy/minbpe/blob/HEAD/minbpe/base.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c202c7e568439b5"}},{"code_sha256_prefix":"15d9c32bbe7da76f","entry":"replace_control_characters","repo":"karpathy/minbpe","repo_kind":"listed","path":"minbpe/base.py","file_url":"https://github.com/karpathy/minbpe/blob/HEAD/minbpe/base.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15d9c32bbe7da76f"}},{"code_sha256_prefix":"d1027b3c5283677a","entry":"replace_pair","repo":"kh-mo/QA_wikisql","repo_kind":"listed","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1027b3c5283677a"}},{"code_sha256_prefix":"684c47713cee0e44","entry":"replace_pair","repo":"thinkwee/DPP_CNN_Summarization","repo_kind":"listed","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"684c47713cee0e44"}},{"code_sha256_prefix":"ab293eff6ffc4b69","entry":"replace_pair","repo":"rsennrich/subword-nmt","repo_kind":"official","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/rsennrich/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab293eff6ffc4b69"}},{"code_sha256_prefix":"c0d8d4efee4a4015","entry":"selective_get_stats","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0d8d4efee4a4015"}},{"code_sha256_prefix":"293d3695d53b0cb1","entry":"Tokenizer","repo":"karpathy/minbpe","repo_kind":"listed","path":"minbpe/base.py","file_url":"https://github.com/karpathy/minbpe/blob/HEAD/minbpe/base.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":"293d3695d53b0cb1"}},{"code_sha256_prefix":"800b6a080cb3c624","entry":"_get_vocabulary","repo":"rsennrich/subword-nmt","repo_kind":"official","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/rsennrich/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.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":"800b6a080cb3c624"}},{"code_sha256_prefix":"133f6dc75e90bbd6","entry":"_learn_bpe","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"133f6dc75e90bbd6"}},{"code_sha256_prefix":"0c8c96b6d6bd911a","entry":"learn_bpe","repo":"thinkwee/DPP_CNN_Summarization","repo_kind":"listed","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c8c96b6d6bd911a"}},{"code_sha256_prefix":"d86dc2151a1bd58e","entry":"learn_bpe","repo":"rsennrich/subword-nmt","repo_kind":"official","path":"subword_nmt/learn_bpe.py","file_url":"https://github.com/rsennrich/subword-nmt/blob/HEAD/subword_nmt/learn_bpe.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":"d86dc2151a1bd58e"}},{"code_sha256_prefix":"927c3c1d2631e415","entry":"prune_stats","repo":"thinkwee/DPP_CNN_Summarization","repo_kind":"listed","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"927c3c1d2631e415"}},{"code_sha256_prefix":"e2122ad711c160ec","entry":"save_voca","repo":"SeonbeomKim/Python-Byte_Pair_Encoding","repo_kind":"listed","path":"bpe_module/learn_BPE.py","file_url":"https://github.com/SeonbeomKim/Python-Byte_Pair_Encoding/blob/HEAD/bpe_module/learn_BPE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2122ad711c160ec"}},{"code_sha256_prefix":"c5fcb9cba4915130","entry":"update_pair_statistics","repo":"kh-mo/QA_wikisql","repo_kind":"listed","path":"learn_bpe.py","file_url":"https://github.com/kh-mo/QA_wikisql/blob/HEAD/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c5fcb9cba4915130"}},{"code_sha256_prefix":"718aeb6813392ac3","entry":"update_pair_statistics","repo":"thinkwee/DPP_CNN_Summarization","repo_kind":"listed","path":"fairseq/raw_dataset/subword_nmt/learn_bpe.py","file_url":"https://github.com/thinkwee/DPP_CNN_Summarization/blob/HEAD/fairseq/raw_dataset/subword_nmt/learn_bpe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"718aeb6813392ac3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}