{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/universal-dependencies","name":"Universal Dependencies","full_name":null,"description_markdown":"The **Universal Dependencies** (UD) project seeks to develop cross-linguistically consistent treebank annotation of morphology and syntax for multiple languages. The first version of the dataset was released in 2015 and consisted of 10 treebanks over 10 languages. Version 2.7 released in 2020 consists of 183 treebanks over 104 languages. The annotation consists of UPOS (universal part-of-speech tags), XPOS (language-specific part-of-speech tags), Feats (universal morphological features), Lemmas, dependency heads and universal dependency labels.\r\n\r\nSource: [Evaluating Contextualized Embeddings on 54 Languagesin POS Tagging, Lemmatization and Dependency Parsing](https://arxiv.org/abs/1908.07448)\r\nImage Source: [https://universaldependencies.org/introduction.html](https://universaldependencies.org/introduction.html)","description_withheld":null,"homepage":"https://universaldependencies.org/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/universal-dependencies-v1-a-multilingual","title":"Universal Dependencies v1: A Multilingual Treebank Collection","first_author":"Joakim Nivre","url":null},"license":{"name":"Various (see link)","url":"https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.1"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"},{"name":"POS","url":"/task/pos","datasets_with_task":"/datasets/task/pos"},{"name":"Cross-lingual zero-shot dependency parsing","url":"/task/cross-lingual-zero-shot-dependency-parsing","datasets_with_task":"/datasets/task/cross-lingual-zero-shot-dependency-parsing"},{"name":"Cross-Lingual POS Tagging","url":"/task/cross-lingual-pos-tagging","datasets_with_task":"/datasets/task/cross-lingual-pos-tagging"},{"name":"TAG","url":"/task/tag","datasets_with_task":"/datasets/task/tag"},{"name":"SENTS","url":"/task/sents","datasets_with_task":"/datasets/task/sents"},{"name":"MORPH","url":"/task/morph","datasets_with_task":"/datasets/task/morph"},{"name":"UNLABELED_DEPENDENCIES","url":"/task/unlabeled-dependencies","datasets_with_task":"/datasets/task/unlabeled-dependencies"},{"name":"LABELED_DEPENDENCIES","url":"/task/labeled-dependencies","datasets_with_task":"/datasets/task/labeled-dependencies"},{"name":"LEMMA","url":"/task/lemma","datasets_with_task":"/datasets/task/lemma"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Afrikaans","url":"/datasets/language/afrikaans"},{"name":"Akkadian","url":"/datasets/language/akkadian"},{"name":"Akuntsu","url":"/datasets/language/akuntsu"},{"name":"Albanian","url":"/datasets/language/albanian"},{"name":"Amharic","url":"/datasets/language/amharic"},{"name":"Ancient Greek","url":"/datasets/language/ancient-greek"},{"name":"Apurinã","url":"/datasets/language/apurin"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Armenian","url":"/datasets/language/armenian"},{"name":"Assyrian Neo-Aramaic","url":"/datasets/language/assyrian-neo-aramaic"},{"name":"Bambara","url":"/datasets/language/bambara"},{"name":"Basque","url":"/datasets/language/basque"},{"name":"Belarusian","url":"/datasets/language/belarusian"},{"name":"Bhojpuri","url":"/datasets/language/bhojpuri"},{"name":"Breton","url":"/datasets/language/breton"},{"name":"Bulgarian","url":"/datasets/language/bulgarian"},{"name":"Catalan","url":"/datasets/language/catalan"},{"name":"Chukot","url":"/datasets/language/chukot"},{"name":"Church Slavic","url":"/datasets/language/church-slavic"},{"name":"Coptic","url":"/datasets/language/coptic"},{"name":"Croatian","url":"/datasets/language/croatian"},{"name":"Czech","url":"/datasets/language/czech"},{"name":"Danish","url":"/datasets/language/danish"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Erzya","url":"/datasets/language/erzya"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Faroese","url":"/datasets/language/faroese"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Galician","url":"/datasets/language/galician"},{"name":"Gothic","url":"/datasets/language/gothic"},{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Icelandic","url":"/datasets/language/icelandic"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Irish","url":"/datasets/language/irish"},{"name":"Karelian","url":"/datasets/language/karelian"},{"name":"Kazakh","url":"/datasets/language/kazakh"},{"name":"Khunsari","url":"/datasets/language/khunsari"},{"name":"Komi-Permyak","url":"/datasets/language/komi-permyak"},{"name":"Komi-Zyrian","url":"/datasets/language/komi-zyrian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Latin","url":"/datasets/language/latin"},{"name":"Latvian","url":"/datasets/language/latvian"},{"name":"Literary Chinese","url":"/datasets/language/literary-chinese"},{"name":"Lithuanian","url":"/datasets/language/lithuanian"},{"name":"Livvi","url":"/datasets/language/livvi"},{"name":"Maltese","url":"/datasets/language/maltese"},{"name":"Manx","url":"/datasets/language/manx"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Mbyá Guaraní","url":"/datasets/language/mby-guaran"},{"name":"Modern Greek","url":"/datasets/language/modern-greek"},{"name":"Moksha","url":"/datasets/language/moksha"},{"name":"Mundurukú","url":"/datasets/language/munduruk"},{"name":"Nayini","url":"/datasets/language/nayini"},{"name":"Nigerian Pidgin","url":"/datasets/language/nigerian-pidgin"},{"name":"Northern Kurdish","url":"/datasets/language/northern-kurdish"},{"name":"Northern Sami","url":"/datasets/language/northern-sami"},{"name":"Norwegian","url":"/datasets/language/norwegian"},{"name":"Old French","url":"/datasets/language/old-french"},{"name":"Old Russian","url":"/datasets/language/old-russian"},{"name":"Old Turkish","url":"/datasets/language/old-turkish"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Romanian","url":"/datasets/language/romanian"},{"name":"Russia Buriat","url":"/datasets/language/russia-buriat"},{"name":"Sanskrit","url":"/datasets/language/sanskrit"},{"name":"Scottish Gaelic","url":"/datasets/language/scottish-gaelic"},{"name":"Serbian","url":"/datasets/language/serbian"},{"name":"Skolt Sami","url":"/datasets/language/skolt-sami"},{"name":"Slovak","url":"/datasets/language/slovak"},{"name":"Slovenian","url":"/datasets/language/slovenian"},{"name":"Soi","url":"/datasets/language/soi"},{"name":"South Levantine Arabic","url":"/datasets/language/south-levantine-arabic"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Swedish Sign Language","url":"/datasets/language/swedish-sign-language"},{"name":"Swiss German","url":"/datasets/language/swiss-german"},{"name":"Tagalog","url":"/datasets/language/tagalog"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Tupinambá","url":"/datasets/language/tupinamb"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Uighur","url":"/datasets/language/uighur"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"},{"name":"Upper Sorbian","url":"/datasets/language/upper-sorbian"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Warlpiri","url":"/datasets/language/warlpiri"},{"name":"Welsh","url":"/datasets/language/welsh"},{"name":"Wolof","url":"/datasets/language/wolof"},{"name":"Yoruba","url":"/datasets/language/yoruba"},{"name":"Yue Chinese","url":"/datasets/language/yue-chinese"}],"variants":["UD","Universal Dependencies","Universal Dependency Treebank","Universal Dependencies v2.8","universal_dependencies sk_snk","Maltese Universal Dependencies Treebank (MUDT)","UD Danish DDT"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/universal_dependencies","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/albertvillanova/universal_dependencies","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BramVanroy/ud_dutch_lassysmall","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/BramVanroy/ud_dutch_alpino","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/universal-dependencies/universal_dependencies","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/structured_prediction/dataset_readers/universal_dependencies/","frameworks":["pytorch"]}],"num_papers_in_archive":520,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dependency-parsing-on-universal-dependencies","task":"Dependency Parsing","dataset_variant":"Universal Dependencies","rows":6,"metrics":["LAS","UAS","BLEX"],"first_row_in_archive_order":{"model":"UDPipe 2.0 + mBERT + FLAIR","paper":"/paper/evaluating-contextualized-embeddings-on-54","metrics":{"LAS":"84.60","UAS":"87.64"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/part-of-speech-tagging-on-ud","task":"Part-Of-Speech Tagging","dataset_variant":"UD","rows":5,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"BiLSTM-LAN","paper":"/paper/hierarchically-refined-label-attention","metrics":{"Avg accuracy":"96.88"},"code_links":[{"title":"Nealcly/LAN","url":"https://github.com/Nealcly/LAN"},{"title":"Nealcly/BiLSTM-LAN","url":"https://github.com/Nealcly/BiLSTM-LAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-zero-shot-dependency-parsing-on","task":"Cross-lingual zero-shot dependency parsing","dataset_variant":"Universal Dependency Treebank","rows":3,"metrics":["LAS","UAS"],"first_row_in_archive_order":{"model":"Cross-Lingual ELMo","paper":"/paper/cross-lingual-alignment-of-contextual-word","metrics":{"LAS":"77.3","UAS":"84.2"},"code_links":[{"title":"TalSchuster/CrossLingualContextualEmb","url":"https://github.com/TalSchuster/CrossLingualContextualEmb"},{"title":"TalSchuster/CrossLingualELMo","url":"https://github.com/TalSchuster/CrossLingualELMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dependency-parsing-on-universal-dependency","task":"Dependency Parsing","dataset_variant":"Universal Dependency Treebank","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"Stanza","paper":"/paper/stanza-a-python-natural-language-processing","metrics":{"Macro F1":"81.13"},"code_links":[{"title":"stanfordnlp/stanza","url":"https://github.com/stanfordnlp/stanza"},{"title":"textflint/textflint","url":"https://github.com/textflint/textflint"},{"title":"astrazeneca/kazu","url":"https://github.com/astrazeneca/kazu"},{"title":"sktwtrg/stanza_ja_test","url":"https://github.com/sktwtrg/stanza_ja_test"},{"title":"rasoolims/stanza","url":"https://github.com/rasoolims/stanza"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-identification-on-universal","task":"Language Identification","dataset_variant":"Universal Dependencies","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Apple bi-LSTM","paper":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","metrics":{"Accuracy":"86.93"},"code_links":[{"title":"AU-DIS/LSTM_langid","url":"https://github.com/AU-DIS/LSTM_langid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":16,"of":16,"counts":{"papers_with_a_benchmark_row":16,"with_a_code_link":12,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","slug":"a-reproduction-of-apple-s-bi-directional-lstm","title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","date":"2021-02-11","arxiv_id":"2102.06282","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stanza-a-python-natural-language-processing","slug":"stanza-a-python-natural-language-processing","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","date":"2020-03-16","arxiv_id":"2003.07082","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":30,"samples_ran":16,"samples_constructed":8,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":14,"pointer_only_for_licence":28,"official":{"repos":["stanfordnlp/stanza"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stanza-a-python-natural-language-processing#ran","syntology_url":"https://syntology.ai/paper/2003.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07082"}}}},{"paper":"/paper/hierarchically-refined-label-attention","slug":"hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","date":"2019-08-23","arxiv_id":"1908.08676","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/evaluating-contextualized-embeddings-on-54","slug":"evaluating-contextualized-embeddings-on-54","title":"Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing","date":"2019-08-20","arxiv_id":"1908.07448","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sequence-tagging-with-contextual-and-non","slug":"sequence-tagging-with-contextual-and-non","title":"Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation","date":"2019-06-04","arxiv_id":"1906.01569","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/75-languages-1-model-parsing-universal","slug":"75-languages-1-model-parsing-universal","title":"75 Languages, 1 Model: Parsing Universal Dependencies Universally","date":"2019-04-03","arxiv_id":"1904.02099","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["hyperparticle/udify"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/75-languages-1-model-parsing-universal#ran","syntology_url":"https://syntology.ai/paper/1904.02099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02099"}}}},{"paper":"/paper/cross-lingual-alignment-of-contextual-word","slug":"cross-lingual-alignment-of-contextual-word","title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing","date":"2019-02-25","arxiv_id":"1902.09492","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["TalSchuster/CrossLingualELMo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-alignment-of-contextual-word#ran","syntology_url":"https://syntology.ai/paper/1902.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09492"}}}},{"paper":"/paper/universal-dependency-parsing-from-scratch","slug":"universal-dependency-parsing-from-scratch","title":"Universal Dependency Parsing from Scratch","date":"2019-01-29","arxiv_id":"1901.10457","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/turku-neural-parser-pipeline-an-end-to-end","slug":"turku-neural-parser-pipeline-an-end-to-end","title":"Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/udpipe-20-prototype-at-conll-2018-ud-shared","slug":"udpipe-20-prototype-at-conll-2018-ud-shared","title":"UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-better-ud-parsing-deep-contextualized","slug":"towards-better-ud-parsing-deep-contextualized","title":"Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation","date":"2018-07-09","arxiv_id":"1807.03121","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-multilingual-part-of-speech-tagging","slug":"robust-multilingual-part-of-speech-tagging","title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","date":"2017-11-14","arxiv_id":"1711.04903","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-novel-neural-network-model-for-joint-pos","slug":"a-novel-neural-network-model-for-joint-pos","title":"A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing","date":"2017-05-16","arxiv_id":"1705.05952","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-part-of-speech-tagging-with","slug":"multilingual-part-of-speech-tagging-with","title":"Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss","date":"2016-04-19","arxiv_id":"1604.05529","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["bplank/bilstm-aux"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multilingual-part-of-speech-tagging-with#ran","syntology_url":"https://syntology.ai/paper/1604.05529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.05529"}}}},{"paper":"/paper/a-representation-learning-framework-for-multi","slug":"a-representation-learning-framework-for-multi","title":"A Representation Learning Framework for Multi-Source Transfer Parsing","date":"2016-03-05","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/many-languages-one-parser","slug":"many-languages-one-parser","title":"Many Languages, One Parser","date":"2016-02-04","arxiv_id":"1602.01595","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/a-reproduction-of-apple-s-bi-directional-lstm","slug":"a-reproduction-of-apple-s-bi-directional-lstm","title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","date":"2021-02-11","arxiv_id":"2102.06282","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stanza-a-python-natural-language-processing","slug":"stanza-a-python-natural-language-processing","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","date":"2020-03-16","arxiv_id":"2003.07082","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":30,"samples_ran":16,"samples_constructed":8,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":14,"pointer_only_for_licence":28,"official":{"repos":["stanfordnlp/stanza"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/stanza-a-python-natural-language-processing#ran","syntology_url":"https://syntology.ai/paper/2003.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07082"}}}},{"paper":"/paper/hierarchically-refined-label-attention","slug":"hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","date":"2019-08-23","arxiv_id":"1908.08676","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/evaluating-contextualized-embeddings-on-54","slug":"evaluating-contextualized-embeddings-on-54","title":"Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing","date":"2019-08-20","arxiv_id":"1908.07448","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sequence-tagging-with-contextual-and-non","slug":"sequence-tagging-with-contextual-and-non","title":"Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation","date":"2019-06-04","arxiv_id":"1906.01569","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/75-languages-1-model-parsing-universal","slug":"75-languages-1-model-parsing-universal","title":"75 Languages, 1 Model: Parsing Universal Dependencies Universally","date":"2019-04-03","arxiv_id":"1904.02099","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["hyperparticle/udify"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/75-languages-1-model-parsing-universal#ran","syntology_url":"https://syntology.ai/paper/1904.02099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02099"}}}},{"paper":"/paper/cross-lingual-alignment-of-contextual-word","slug":"cross-lingual-alignment-of-contextual-word","title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing","date":"2019-02-25","arxiv_id":"1902.09492","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["TalSchuster/CrossLingualELMo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-lingual-alignment-of-contextual-word#ran","syntology_url":"https://syntology.ai/paper/1902.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09492"}}}},{"paper":"/paper/universal-dependency-parsing-from-scratch","slug":"universal-dependency-parsing-from-scratch","title":"Universal Dependency Parsing from Scratch","date":"2019-01-29","arxiv_id":"1901.10457","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/turku-neural-parser-pipeline-an-end-to-end","slug":"turku-neural-parser-pipeline-an-end-to-end","title":"Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/udpipe-20-prototype-at-conll-2018-ud-shared","slug":"udpipe-20-prototype-at-conll-2018-ud-shared","title":"UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-better-ud-parsing-deep-contextualized","slug":"towards-better-ud-parsing-deep-contextualized","title":"Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation","date":"2018-07-09","arxiv_id":"1807.03121","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-multilingual-part-of-speech-tagging","slug":"robust-multilingual-part-of-speech-tagging","title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","date":"2017-11-14","arxiv_id":"1711.04903","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-novel-neural-network-model-for-joint-pos","slug":"a-novel-neural-network-model-for-joint-pos","title":"A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing","date":"2017-05-16","arxiv_id":"1705.05952","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-part-of-speech-tagging-with","slug":"multilingual-part-of-speech-tagging-with","title":"Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss","date":"2016-04-19","arxiv_id":"1604.05529","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["bplank/bilstm-aux"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multilingual-part-of-speech-tagging-with#ran","syntology_url":"https://syntology.ai/paper/1604.05529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.05529"}}}},{"paper":"/paper/a-representation-learning-framework-for-multi","slug":"a-representation-learning-framework-for-multi","title":"A Representation Learning Framework for Multi-Source Transfer Parsing","date":"2016-03-05","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/many-languages-one-parser","slug":"many-languages-one-parser","title":"Many Languages, One Parser","date":"2016-02-04","arxiv_id":"1602.01595","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/universal-dependencies/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/universal-dependencies/papers/ran/1","json":"/dataset/universal-dependencies/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":49,"samples_ran":31,"samples_constructed":8,"samples_ran_checked":23,"samples_ran_instrument_failed":8,"samples_unverified":18,"pointer_only_for_licence":29,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1de03922c295ae9905676882cdb377c33b97f10ef24dc5e813030e0e7d9a00a2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}