{"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/word2word-a-collection-of-bilingual-lexicons","title":"word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs","arxiv_id":"1911.12019","date":"2019-11-27","proceeding":"LREC 2020 5","authors":["Yo Joong Choe","Kyubyong Park","Dongwoo Kim"],"abstract":"We present word2word, a publicly available dataset and an open-source Python package for cross-lingual word translations extracted from sentence-level parallel corpora. Our dataset provides top-k word translations in 3,564 (directed) language pairs across 62 languages in OpenSubtitles2018 (Lison et al., 2018). To obtain this dataset, we use a count-based bilingual lexicon extraction model based on the observation that not only source and target words but also source words themselves can be highly correlated. We illustrate that the resulting bilingual lexicons have high coverage and attain competitive translation quality for several language pairs. We wrap our dataset and model in an easy-to-use Python library, which supports downloading and retrieving top-k word translations in any of the supported language pairs as well as computing top-k word translations for custom parallel corpora.","url_abs":"https://arxiv.org/abs/1911.12019v1","url_pdf":"https://arxiv.org/pdf/1911.12019v1.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":"word2word-a-collection-of-bilingual-lexicons","repo_url":"https://github.com/Kyubyong/word2word","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"word2word-a-collection-of-bilingual-lexicons","repo_url":"https://github.com/kakaobrain/word2word","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"word2word","name":"word2word","full_name":"word2word"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1911.12019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12019"}},"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/kakaobrain/word2word","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kyubyong/word2word","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"unverified":10},"by_repo_kind":{"listed":{"samples":12,"ran":2,"repositories":2}},"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":"d9951e08e23cfb5e","entry":"get_trans_co","repo":"kakaobrain/word2word","repo_kind":"listed","path":"word2word/methods.py","file_url":"https://github.com/kakaobrain/word2word/blob/HEAD/word2word/methods.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9951e08e23cfb5e"}},{"code_sha256_prefix":"91ef2e84a38bc63c","entry":"rerank","repo":"kakaobrain/word2word","repo_kind":"listed","path":"word2word/methods.py","file_url":"https://github.com/kakaobrain/word2word/blob/HEAD/word2word/methods.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91ef2e84a38bc63c"}},{"code_sha256_prefix":"0d33bb20d13f72b5","entry":"convert_google_translate","repo":"Kyubyong/word2word","repo_kind":"listed","path":"google_grader.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/google_grader.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":"0d33bb20d13f72b5"}},{"code_sha256_prefix":"b4213b13fbb65ec1","entry":"exists","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/utils.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/utils.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":"b4213b13fbb65ec1"}},{"code_sha256_prefix":"4b2978de4060aa1c","entry":"get_download_url","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/utils.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/utils.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":"4b2978de4060aa1c"}},{"code_sha256_prefix":"028299bfe6ab9a2c","entry":"get_google_translate","repo":"Kyubyong/word2word","repo_kind":"listed","path":"google_grader.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/google_grader.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":"028299bfe6ab9a2c"}},{"code_sha256_prefix":"cd493b05c9546aa3","entry":"get_savedir","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/utils.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/utils.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":"cd493b05c9546aa3"}},{"code_sha256_prefix":"0297c4a1fef5186d","entry":"get_survey_summary_reference","repo":"Kyubyong/word2word","repo_kind":"listed","path":"google_grader.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/google_grader.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":"0297c4a1fef5186d"}},{"code_sha256_prefix":"349ed3bbc388de65","entry":"load_tokenizer","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/tokenization.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/tokenization.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":"349ed3bbc388de65"}},{"code_sha256_prefix":"00f3aa78f7c4246f","entry":"process_line","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/tokenization.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/tokenization.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":"00f3aa78f7c4246f"}},{"code_sha256_prefix":"ffa747727408d325","entry":"rerank_mp","repo":"kakaobrain/word2word","repo_kind":"listed","path":"word2word/methods.py","file_url":"https://github.com/kakaobrain/word2word/blob/HEAD/word2word/methods.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":"ffa747727408d325"}},{"code_sha256_prefix":"3fbb2428068ca79f","entry":"word_segment","repo":"Kyubyong/word2word","repo_kind":"listed","path":"word2word/tokenization.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/tokenization.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":"3fbb2428068ca79f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}