{"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/spanish-pre-trained-bert-model-and-evaluation","title":"Spanish Pre-trained BERT Model and Evaluation Data","arxiv_id":"2308.02976","date":"2023-08-06","proceeding":null,"authors":["José Cañete","Gabriel Chaperon","Rodrigo Fuentes","Jou-Hui Ho","Hojin Kang","Jorge Pérez"],"abstract":"The Spanish language is one of the top 5 spoken languages in the world. Nevertheless, finding resources to train or evaluate Spanish language models is not an easy task. In this paper we help bridge this gap by presenting a BERT-based language model pre-trained exclusively on Spanish data. As a second contribution, we also compiled several tasks specifically for the Spanish language in a single repository much in the spirit of the GLUE benchmark. By fine-tuning our pre-trained Spanish model, we obtain better results compared to other BERT-based models pre-trained on multilingual corpora for most of the tasks, even achieving a new state-of-the-art on some of them. We have publicly released our model, the pre-training data, and the compilation of the Spanish benchmarks.","url_abs":"https://arxiv.org/abs/2308.02976v1","url_pdf":"https://arxiv.org/pdf/2308.02976v1.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":"spanish-pre-trained-bert-model-and-evaluation","repo_url":"https://github.com/dccuchile/beto","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"spanish-pre-trained-bert-model-and-evaluation","repo_url":"https://github.com/josecannete/spanish-corpora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.02976","atlas_url":"https://app.syntology.ai/?focus=2308.02976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02976"}},"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/josecannete/spanish-corpora","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dccuchile/beto","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"89f3eac9348b7d97","entry":"remove_listing","repo":"josecannete/spanish-corpora","repo_kind":"official","path":"corpus_processing.py","file_url":"https://github.com/josecannete/spanish-corpora/blob/HEAD/corpus_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89f3eac9348b7d97"}},{"code_sha256_prefix":"63582c062b86a49d","entry":"remove_urls","repo":"josecannete/spanish-corpora","repo_kind":"official","path":"corpus_processing.py","file_url":"https://github.com/josecannete/spanish-corpora/blob/HEAD/corpus_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63582c062b86a49d"}},{"code_sha256_prefix":"c8c1e56997502eec","entry":"replace_multi_whitespaces","repo":"josecannete/spanish-corpora","repo_kind":"official","path":"corpus_processing.py","file_url":"https://github.com/josecannete/spanish-corpora/blob/HEAD/corpus_processing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8c1e56997502eec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}