{"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/stanza-a-python-natural-language-processing","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","arxiv_id":"2003.07082","date":"2020-03-16","proceeding":"ACL 2020 6","authors":["Peng Qi","Yuhao Zhang","Yuhui Zhang","Jason Bolton","Christopher D. Manning"],"abstract":"We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Stanza on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves competitive performance on all languages tested. Additionally, Stanza includes a native Python interface to the widely used Java Stanford CoreNLP software, which further extends its functionality to cover other tasks such as coreference resolution and relation extraction. Source code, documentation, and pretrained models for 66 languages are available at https://stanfordnlp.github.io/stanza.","url_abs":"https://arxiv.org/abs/2003.07082v2","url_pdf":"https://arxiv.org/pdf/2003.07082v2.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":"stanza-a-python-natural-language-processing","repo_url":"https://github.com/stanfordnlp/stanza","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stanza-a-python-natural-language-processing","repo_url":"https://github.com/astrazeneca/kazu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stanza-a-python-natural-language-processing","repo_url":"https://github.com/rasoolims/stanza","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stanza-a-python-natural-language-processing","repo_url":"https://github.com/sktwtrg/stanza_ja_test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"stanza-a-python-natural-language-processing","repo_url":"https://github.com/textflint/textflint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"lemmatization","task_name":"Lemmatization"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-universal-dependency","task":"Dependency Parsing","dataset":"Universal Dependency Treebank","model":"Stanza","rank_in_archive_order":1,"of":1,"metrics":{"Macro F1":"81.13"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07082"}},"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/textflint/textflint","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astrazeneca/kazu","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rasoolims/stanza","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sktwtrg/stanza_ja_test","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordnlp/stanza","reach":null}],"summary":{"ran":8,"ran_draft_wrong":6,"ran_honours":2,"unverified":14},"by_repo_kind":{"listed":{"samples":30,"ran":16,"repositories":3}},"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":28,"samples":[{"code_sha256_prefix":"487f3b0ec937a54c","entry":"LanguageNotDownloadedError","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"487f3b0ec937a54c"}},{"code_sha256_prefix":"a94def2bd6a7ccef","entry":"PipelineRequirementsException","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a94def2bd6a7ccef"}},{"code_sha256_prefix":"1cef00c50c37865a","entry":"ProcessorRequirementsException","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1cef00c50c37865a"}},{"code_sha256_prefix":"3c4ad0bcfb16d5be","entry":"ResourcesFileNotFoundError","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3c4ad0bcfb16d5be"}},{"code_sha256_prefix":"0e18204770d6deba","entry":"Span","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0e18204770d6deba"}},{"code_sha256_prefix":"efbc8e704c469812","entry":"UnknownProcessorError","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"efbc8e704c469812"}},{"code_sha256_prefix":"fa59630684efd448","entry":"UnsupportedProcessorError","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fa59630684efd448"}},{"code_sha256_prefix":"b4bf015cd773f71a","entry":"Word","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b4bf015cd773f71a"}},{"code_sha256_prefix":"ac5b9379b4a25fab","entry":"add_dependencies","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ac5b9379b4a25fab"}},{"code_sha256_prefix":"5b9700dd4e79767e","entry":"build_default_config","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5b9700dd4e79767e"}},{"code_sha256_prefix":"5f0cbc33871edc10","entry":"decode_from_bioes","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5f0cbc33871edc10"}},{"code_sha256_prefix":"99a85098b6a5141d","entry":"make_table","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"99a85098b6a5141d"}},{"code_sha256_prefix":"675808015d0470da","entry":"process_pipeline_parameters","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"675808015d0470da"}},{"code_sha256_prefix":"27de771fb9f31bfe","entry":"set_logging_level","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"27de771fb9f31bfe"}},{"code_sha256_prefix":"043d8e3c67dae7ca","entry":"sort_processors","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"043d8e3c67dae7ca"}},{"code_sha256_prefix":"c029ebc04574e452","entry":"textflint_url","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.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":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c029ebc04574e452"}},{"code_sha256_prefix":"4e1f6acc9f7afd42","entry":"CnProcessor","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4e1f6acc9f7afd42"}},{"code_sha256_prefix":"083805d359d8b214","entry":"Document","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"083805d359d8b214"}},{"code_sha256_prefix":"532c3601f567e34e","entry":"Pipeline","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"532c3601f567e34e"}},{"code_sha256_prefix":"a593aad35ac72786","entry":"Sentence","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"a593aad35ac72786"}},{"code_sha256_prefix":"fd5106dbf3a3eab0","entry":"StanzaObject","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"fd5106dbf3a3eab0"}},{"code_sha256_prefix":"9b73f8e94f1d04b0","entry":"Token","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"9b73f8e94f1d04b0"}},{"code_sha256_prefix":"d032599118dda649","entry":"_readonly_setter","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"d032599118dda649"}},{"code_sha256_prefix":"ce671eb8cef8d1ff","entry":"download_if_needed","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ce671eb8cef8d1ff"}},{"code_sha256_prefix":"521a7a9935db7206","entry":"http_get","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"521a7a9935db7206"}},{"code_sha256_prefix":"afd5ff16f515d398","entry":"maintain_processor_list","repo":"rasoolims/stanza","repo_kind":"listed","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.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":"afd5ff16f515d398"}},{"code_sha256_prefix":"412da2f1d85884ca","entry":"multi_label_forward","repo":"astrazeneca/kazu","repo_kind":"listed","path":"kazu/training/modelling.py","file_url":"https://github.com/astrazeneca/kazu/blob/HEAD/kazu/training/modelling.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":"412da2f1d85884ca"}},{"code_sha256_prefix":"ca38aac5ce43ae41","entry":"path_in_cache","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ca38aac5ce43ae41"}},{"code_sha256_prefix":"21d5beba42458a9a","entry":"unzip_file","repo":"textflint/textflint","repo_kind":"listed","path":"textflint/common/preprocess/cn_processor.py","file_url":"https://github.com/textflint/textflint/blob/HEAD/textflint/common/preprocess/cn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"21d5beba42458a9a"}},{"code_sha256_prefix":"2e08287c21f3b1dc","entry":"wait_for_model_pack_completion","repo":"astrazeneca/kazu","repo_kind":"listed","path":"kazu/utils/build_and_test_model_packs.py","file_url":"https://github.com/astrazeneca/kazu/blob/HEAD/kazu/utils/build_and_test_model_packs.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":"2e08287c21f3b1dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}