{"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/enriching-word-vectors-with-subword","title":"Enriching Word Vectors with Subword Information","arxiv_id":"1607.04606","date":"2016-07-15","proceeding":"TACL 2017 1","authors":["Piotr Bojanowski","Edouard Grave","Armand Joulin","Tomas Mikolov"],"abstract":"Continuous word representations, trained on large unlabeled corpora are\nuseful for many natural language processing tasks. Popular models that learn\nsuch representations ignore the morphology of words, by assigning a distinct\nvector to each word. This is a limitation, especially for languages with large\nvocabularies and many rare words. In this paper, we propose a new approach\nbased on the skipgram model, where each word is represented as a bag of\ncharacter $n$-grams. A vector representation is associated to each character\n$n$-gram; words being represented as the sum of these representations. Our\nmethod is fast, allowing to train models on large corpora quickly and allows us\nto compute word representations for words that did not appear in the training\ndata. We evaluate our word representations on nine different languages, both on\nword similarity and analogy tasks. By comparing to recently proposed\nmorphological word representations, we show that our vectors achieve\nstate-of-the-art performance on these tasks.","url_abs":"http://arxiv.org/abs/1607.04606v2","url_pdf":"http://arxiv.org/pdf/1607.04606v2.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":"enriching-word-vectors-with-subword","repo_url":"https://github.com/facebookresearch/fastText","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/Babylonpartners/fastText_multilingual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/DW-yejing/fasttext4j-jdk6","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/FengJiaChunFromSYSU/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/GitHubSprint/fasttext4j","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/Kinetikm/fastTextRelearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/Kinetikm/fasttextRelearnExperiment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/M155K4R4/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/MhYao2014/HyperbolicEmbedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/MirkoLenz/ReCAP-Argument-Graph-Retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/Nim-NLP/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/Omerktn/fastText-iterative","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ReCAP-UTR/Argument-Graph-Retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/SarangShaikh201/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ahmedssabir/Visual-Semantic-Relatedness-with-Word-Embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/amymariaparker2401/new","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/babylonhealth/fastText_multilingual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/bamtercelboo/cw2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/bung87/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/currentsapi/fastlangid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/dbaumgarten/FToDTF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/divisionai/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ericxsun/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/explosion/floret","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/hufscapstone/Fast_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/indix/whatthelang","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/jen1995/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/kpu/fastertext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/labdac/charlacompling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/linkfluence/fastText4j","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/lmd1993/fastTextBoost","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/luckyPT/jvm-ml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/luhuiguo/jfasttext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/mrzzy/np-dl-assign-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/mwydmuch/extremeText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/oapio/nlp-chinese-experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/plasticityai/magnitude","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/pommedeterresautee/fastrtext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ppke-nlpg/fastText_factored-cbow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/rmenegaux/fastDNA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/romik9999/fasttext-1925f09ed3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/trietnm2/sent2vec4j","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/tshev/faster-FastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ulf1/augtxt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/vackosar/fasttext-vector-norms-and-oov-words","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/vinhkhuc/JFastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/wyfish/fastText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/xuzhezhaozhao/fastText_reading","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/zhang2010hao/cw2vec-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/fasttext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/ZZhangyutong/fasttext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/cui0523/Code6/tree/main/fasttext","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/dmlc/gluon-nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enriching-word-vectors-with-subword","repo_url":"https://github.com/harshvivek14/NLP-Word-Embedding-Techniques","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[{"method_slug":"fasttext","method_name":"fastText"}],"datasets_introduced":[],"methods_introduced":[{"slug":"fasttext","name":"fastText","full_name":"fastText"}],"results":[{"leaderboard":"/sota/word-similarity-on-ws353","task":"Word Similarity","dataset":"WS353","model":"SkipGram","rank_in_archive_order":3,"of":3,"metrics":{"Spearman's Rho":"61.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.04606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.04606"}},"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/FengJiaChunFromSYSU/fastText","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GitHubSprint/fasttext4j","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labdac/charlacompling","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bung87/fastText","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amymariaparker2401/new","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/M155K4R4/fastText","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pommedeterresautee/fastrtext","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plasticityai/magnitude","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ericxsun/fastText","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luckyPT/jvm-ml","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oapio/nlp-chinese-experiments","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vinhkhuc/JFastText","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mrzzy/np-dl-assign-2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MirkoLenz/ReCAP-Argument-Graph-Retrieval","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ulf1/augtxt","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/currentsapi/fastlangid","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Omerktn/fastText-iterative","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nim-NLP/fastText","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kinetikm/fastTextRelearning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/divisionai/fastText","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SarangShaikh201/fastText","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rmenegaux/fastDNA","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lmd1993/fastTextBoost","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/gluon-nlp","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kpu/fastertext","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"unverified":27},"by_repo_kind":{"listed":{"samples":31,"ran":4,"repositories":7}},"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":"a16b79c7bc1860e5","entry":"create_lookup_tables","repo":"SarangShaikh201/fastText","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SarangShaikh201/fastText/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a16b79c7bc1860e5"}},{"code_sha256_prefix":"847e1524ed1bff1a","entry":"load_model","repo":"zhang2010hao/cw2vec-pytorch","repo_kind":"listed","path":"cw2vec.py","file_url":"https://github.com/zhang2010hao/cw2vec-pytorch/blob/HEAD/cw2vec.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":"847e1524ed1bff1a"}},{"code_sha256_prefix":"55d2494d83e5c523","entry":"preprocess","repo":"SarangShaikh201/fastText","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SarangShaikh201/fastText/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"55d2494d83e5c523"}},{"code_sha256_prefix":"f697966cbe929024","entry":"read_args","repo":"Omerktn/fastText-iterative","repo_kind":"listed","path":"python/fasttext_module/fasttext/FastText.py","file_url":"https://github.com/Omerktn/fastText-iterative/blob/HEAD/python/fasttext_module/fasttext/FastText.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f697966cbe929024"}},{"code_sha256_prefix":"478a1a9fc517ce62","entry":"char_ngrams","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pymagnitude/converter_shared.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pymagnitude/converter_shared.py","link_basis":"harvester_set","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":"478a1a9fc517ce62"}},{"code_sha256_prefix":"39f3e4d5f2279ff9","entry":"check_glibc_version","repo":"plasticityai/magnitude","repo_kind":"listed","path":"glibc.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/glibc.py","link_basis":"harvester_set","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":"39f3e4d5f2279ff9"}},{"code_sha256_prefix":"411c04ff52be0d9f","entry":"compute_similarity","repo":"Kinetikm/fastTextRelearning","repo_kind":"listed","path":"python/doc/examples/train_unsupervised.py","file_url":"https://github.com/Kinetikm/fastTextRelearning/blob/HEAD/python/doc/examples/train_unsupervised.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":"411c04ff52be0d9f"}},{"code_sha256_prefix":"153d1c4c32072113","entry":"compute_word_similarities","repo":"dbaumgarten/FToDTF","repo_kind":"listed","path":"ftodtf/model.py","file_url":"https://github.com/dbaumgarten/FToDTF/blob/HEAD/ftodtf/model.py","link_basis":"harvester_set","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":"153d1c4c32072113"}},{"code_sha256_prefix":"4464b010ea7987c2","entry":"draw_index","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/typo.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/typo.py","link_basis":"harvester_set","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":"4464b010ea7987c2"}},{"code_sha256_prefix":"839d40e2e8ad110b","entry":"drop_word","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/order.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/order.py","link_basis":"harvester_set","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":"839d40e2e8ad110b"}},{"code_sha256_prefix":"6e32ac79f67582c1","entry":"entropy","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pymagnitude/converter.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pymagnitude/converter.py","link_basis":"harvester_set","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":"6e32ac79f67582c1"}},{"code_sha256_prefix":"dee6b2dc58e092d3","entry":"fast_md5_file","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pymagnitude/converter_shared.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pymagnitude/converter_shared.py","link_basis":"harvester_set","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":"dee6b2dc58e092d3"}},{"code_sha256_prefix":"8742e7667cc1dafa","entry":"find_index","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/keyboard_layouts.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/keyboard_layouts.py","link_basis":"harvester_set","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":"8742e7667cc1dafa"}},{"code_sha256_prefix":"b5b7c0a5146de532","entry":"generate_ngram_per_word","repo":"dbaumgarten/FToDTF","repo_kind":"listed","path":"ftodtf/input.py","file_url":"https://github.com/dbaumgarten/FToDTF/blob/HEAD/ftodtf/input.py","link_basis":"harvester_set","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":"b5b7c0a5146de532"}},{"code_sha256_prefix":"cde234836e3f3978","entry":"get_batches","repo":"SarangShaikh201/fastText","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SarangShaikh201/fastText/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cde234836e3f3978"}},{"code_sha256_prefix":"f546d4abc08099d7","entry":"get_config_var","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pep425tags.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pep425tags.py","link_basis":"harvester_set","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":"f546d4abc08099d7"}},{"code_sha256_prefix":"e3ecbfdb8037b64d","entry":"get_darwin_arches","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pep425tags.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pep425tags.py","link_basis":"harvester_set","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":"e3ecbfdb8037b64d"}},{"code_sha256_prefix":"5066f582560cf77c","entry":"get_flag","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pep425tags.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pep425tags.py","link_basis":"harvester_set","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":"5066f582560cf77c"}},{"code_sha256_prefix":"e0fd811edefc09ba","entry":"have_compatible_glibc","repo":"plasticityai/magnitude","repo_kind":"listed","path":"glibc.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/glibc.py","link_basis":"harvester_set","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":"e0fd811edefc09ba"}},{"code_sha256_prefix":"a89e48d6397ae9ba","entry":"md5_file","repo":"plasticityai/magnitude","repo_kind":"listed","path":"pymagnitude/converter_shared.py","file_url":"https://github.com/plasticityai/magnitude/blob/HEAD/pymagnitude/converter_shared.py","link_basis":"harvester_set","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":"a89e48d6397ae9ba"}},{"code_sha256_prefix":"280281e946bcacff","entry":"merge_words","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/punct.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/punct.py","link_basis":"harvester_set","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":"280281e946bcacff"}},{"code_sha256_prefix":"cf3407d8e4174215","entry":"ngrams_to_vectors","repo":"dbaumgarten/FToDTF","repo_kind":"listed","path":"ftodtf/model.py","file_url":"https://github.com/dbaumgarten/FToDTF/blob/HEAD/ftodtf/model.py","link_basis":"harvester_set","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":"cf3407d8e4174215"}},{"code_sha256_prefix":"fa43a85dd995968e","entry":"pad_to_length","repo":"dbaumgarten/FToDTF","repo_kind":"listed","path":"ftodtf/input.py","file_url":"https://github.com/dbaumgarten/FToDTF/blob/HEAD/ftodtf/input.py","link_basis":"harvester_set","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":"fa43a85dd995968e"}},{"code_sha256_prefix":"00bd40e0432ca4e5","entry":"parse_batch_func","repo":"dbaumgarten/FToDTF","repo_kind":"listed","path":"ftodtf/model.py","file_url":"https://github.com/dbaumgarten/FToDTF/blob/HEAD/ftodtf/model.py","link_basis":"harvester_set","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":"00bd40e0432ca4e5"}},{"code_sha256_prefix":"ff4bb2b5311e1044","entry":"pressed_twice","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/typo.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/typo.py","link_basis":"harvester_set","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":"ff4bb2b5311e1044"}},{"code_sha256_prefix":"4f5bb4400e32b7e9","entry":"random_args","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/augmenters.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/augmenters.py","link_basis":"harvester_set","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":"4f5bb4400e32b7e9"}},{"code_sha256_prefix":"37d343258aa5993a","entry":"remove_syntaxinfo","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/punct.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/punct.py","link_basis":"harvester_set","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":"37d343258aa5993a"}},{"code_sha256_prefix":"2eb54f96aa23c052","entry":"swap_consecutive","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/order.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/order.py","link_basis":"harvester_set","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":"2eb54f96aa23c052"}},{"code_sha256_prefix":"48776fc059b48990","entry":"swap_consecutive","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/typo.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/typo.py","link_basis":"harvester_set","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":"48776fc059b48990"}},{"code_sha256_prefix":"e36a7da38a737dd2","entry":"synonym_replacement","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/wordsubs.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/wordsubs.py","link_basis":"harvester_set","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":"e36a7da38a737dd2"}},{"code_sha256_prefix":"5f310db16b7971c6","entry":"write_twice","repo":"ulf1/augtxt","repo_kind":"listed","path":"augtxt/order.py","file_url":"https://github.com/ulf1/augtxt/blob/HEAD/augtxt/order.py","link_basis":"harvester_set","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":"5f310db16b7971c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}