{"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/bpemb-tokenization-free-pre-trained-subword","title":"BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages","arxiv_id":"1710.02187","date":"2017-10-05","proceeding":"LREC 2018 5","authors":["Benjamin Heinzerling","Michael Strube"],"abstract":"We present BPEmb, a collection of pre-trained subword unit embeddings in 275\nlanguages, based on Byte-Pair Encoding (BPE). In an evaluation using\nfine-grained entity typing as testbed, BPEmb performs competitively, and for\nsome languages bet- ter than alternative subword approaches, while requiring\nvastly fewer resources and no tokenization. BPEmb is available at\nhttps://github.com/bheinzerling/bpemb","url_abs":"http://arxiv.org/abs/1710.02187v1","url_pdf":"http://arxiv.org/pdf/1710.02187v1.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":"bpemb-tokenization-free-pre-trained-subword","repo_url":"https://github.com/bheinzerling/bpemb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1710.02187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.02187"}},"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/bheinzerling/bpemb","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"ba0c4f0aeaa66738","entry":"http_get","repo":"bheinzerling/bpemb","repo_kind":"official","path":"bpemb/util.py","file_url":"https://github.com/bheinzerling/bpemb/blob/HEAD/bpemb/util.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":"ba0c4f0aeaa66738"}},{"code_sha256_prefix":"d96382233d29c015","entry":"http_get_temp","repo":"bheinzerling/bpemb","repo_kind":"official","path":"bpemb/util.py","file_url":"https://github.com/bheinzerling/bpemb/blob/HEAD/bpemb/util.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":"d96382233d29c015"}},{"code_sha256_prefix":"00e5372b8eff03eb","entry":"sentencepiece_load","repo":"bheinzerling/bpemb","repo_kind":"official","path":"bpemb/util.py","file_url":"https://github.com/bheinzerling/bpemb/blob/HEAD/bpemb/util.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":"00e5372b8eff03eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}