Papers › Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2003.07082")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2003.07082", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2003.07082")
Code
No sample from the archive's official repository (stanfordnlp/stanza) is linked to this paper; the 30 samples below come from 3 community repositories. Syntology harvested code from stanfordnlp/stanza for another paper.
stanfordnlp/stanza: Syntology's graph links these samples to Representing and Parsing Korean Constituency Structure at Different Levels of Granularity (arXiv:2608.27035; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.
Syntology 30 code samples harvested from 3 repositories linked to this paper: 16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 30 samples from 3 repositories, 16 ran (10 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- stanfordnlp/stanza, official repository: harvested for another paper, listed under the repository
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
30 samples harvested: 16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 28 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.
412da2f1d85884ca · report
2e08287c21f3b1dc · report
487f3b0ec937a54c · report
fixture: returned LanguageNotDownloadedError · level recorded 2026-09-22 a94def2bd6a7ccef · report
fixture: returned PipelineRequirementsException · level recorded 2026-09-22 1cef00c50c37865a · report
fixture: returned ProcessorRequirementsException · level recorded 2026-09-22 3c4ad0bcfb16d5be · report
fixture: returned ResourcesFileNotFoundError · level recorded 2026-09-22 0e18204770d6deba · report
fixture: returned Span · level recorded 2026-09-22 efbc8e704c469812 · report
fixture: returned UnknownProcessorError · level recorded 2026-09-22 fa59630684efd448 · report
fixture: returned UnsupportedProcessorError · level recorded 2026-09-22 b4bf015cd773f71a · report
fixture: returned Word · level recorded 2026-09-22 ac5b9379b4a25fab · report
fixture: signature resources:dict/0/?, lang:str/0/str, processor_list:list/1/list · returned list · level recorded 2026-09-22 5b9700dd4e79767e · report
fixture: signature resources:dict/0/?, lang:str/0/str, model_dir:str/0/str, load_list:list/1/tuple · returned dict · level recorded 2026-09-22 5f0cbc33871edc10 · report
fixture: signature tags:list/1/str · returned list · level recorded 2026-09-22 99a85098b6a5141d · report
fixture: signature header:list/1/str, content:list/1/list, column_width:NoneType/0/? · returned str · level recorded 2026-09-22 675808015d0470da · report
fixture: signature lang:str/0/str, model_dir:str/0/str, package:str/0/str, processors:str/0/str · returned tuple · level recorded 2026-09-22 27de771fb9f31bfe · report
fixture: signature logging_level:str/0/str, verbose:bool/0/bool · returned int · level recorded 2026-09-22 043d8e3c67dae7ca · report
fixture: signature processor_list:list/1/tuple · returned list · level recorded 2026-09-22 083805d359d8b214 · report
532c3601f567e34e · report
a593aad35ac72786 · report
fd5106dbf3a3eab0 · report
9b73f8e94f1d04b0 · report
d032599118dda649 · report
afd5ff16f515d398 · report
c029ebc04574e452 · report
fixture: signature uri:str/0/str · returned str · level recorded 2026-09-22 4e1f6acc9f7afd42 · report
ce671eb8cef8d1ff · report
521a7a9935db7206 · report
ca38aac5ce43ae41 · report
21d5beba42458a9a · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
2 sibling assemblies for Sta n z a (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Sta n z a (graph method: Sta n z a). 6 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- CnProcessor entry · level 0 · unverified ·
4e1f6acc9f7afd42 - download_if_needed helper · level 0 · unverified ·
ce671eb8cef8d1ff - http_get helper · level 0 · unverified ·
521a7a9935db7206 - path_in_cache helper · level 0 · unverified ·
ca38aac5ce43ae41 - unzip_file helper · level 0 · unverified ·
21d5beba42458a9a - textflint_url helper · level 1 · ran · our draft was wrong ·
c029ebc04574e452
harvested Assembly for Sta n z a (graph method: Sta n z a). 22 bricks; individually on a fixture: 15 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.
one of 2 siblings
- Pipeline entry · level 0 · unverified ·
532c3601f567e34e - Document helper · level 0 · unverified ·
083805d359d8b214 - LanguageNotDownloadedError helper · level 1 · ran ·
487f3b0ec937a54c - PipelineRequirementsException helper · level 1 · ran ·
a94def2bd6a7ccef - ProcessorRequirementsException helper · level 1 · ran ·
1cef00c50c37865a - ResourcesFileNotFoundError helper · level 1 · ran ·
3c4ad0bcfb16d5be - UnsupportedProcessorError helper · level 1 · ran ·
fa59630684efd448 - add_dependencies helper · level 1 · ran · our draft was wrong ·
ac5b9379b4a25fab - build_default_config helper · level 1 · ran · our draft was wrong ·
5b9700dd4e79767e - maintain_processor_list helper · level 0 · unverified ·
afd5ff16f515d398 - make_table helper · level 1 · ran · our draft was wrong ·
99a85098b6a5141d - process_pipeline_parameters helper · level 1 · ran · our draft was wrong ·
675808015d0470da - set_logging_level helper · level 1 · ran · honoured contract ·
27de771fb9f31bfe - sort_processors helper · level 1 · ran · honoured contract ·
043d8e3c67dae7ca - Sentence helper · level 0 · unverified ·
a593aad35ac72786 - StanzaObject helper · level 0 · unverified ·
fd5106dbf3a3eab0 - Word helper · level 1 · ran ·
b4bf015cd773f71a - UnknownProcessorError helper · level 1 · ran ·
efbc8e704c469812 - Span helper · level 1 · ran ·
0e18204770d6deba - Token helper · level 0 · unverified ·
9b73f8e94f1d04b0 - decode_from_bioes helper · level 1 · ran · our draft was wrong ·
5f0cbc33871edc10 - _readonly_setter helper · level 0 · unverified ·
d032599118dda649
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2003.07082") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Dependency Parsing | Universal Dependency Treebank | Stanza | Macro F1 | 81.13 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections