{"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/75-languages-1-model-parsing-universal","title":"75 Languages, 1 Model: Parsing Universal Dependencies Universally","arxiv_id":"1904.02099","date":"2019-04-03","proceeding":"IJCNLP 2019 11","authors":["Dan Kondratyuk","Milan Straka"],"abstract":"We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tuning it on all datasets concatenated together with simple softmax classifiers for each UD task can result in state-of-the-art UPOS, UFeats, Lemmas, UAS, and LAS scores, without requiring any recurrent or language-specific components. We evaluate UDify for multilingual learning, showing that low-resource languages benefit the most from cross-linguistic annotations. We also evaluate for zero-shot learning, with results suggesting that multilingual training provides strong UD predictions even for languages that neither UDify nor BERT have ever been trained on. Code for UDify is available at https://github.com/hyperparticle/udify.","url_abs":"https://arxiv.org/abs/1904.02099v3","url_pdf":"https://arxiv.org/pdf/1904.02099v3.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":"75-languages-1-model-parsing-universal","repo_url":"https://github.com/hyperparticle/udify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"75-languages-1-model-parsing-universal","repo_url":"https://github.com/ahmetustun/udapter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"75-languages-1-model-parsing-universal","repo_url":"https://github.com/idiap/g2g-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-french-gsd","task":"Dependency Parsing","dataset":"French GSD","model":"UDify","rank_in_archive_order":2,"of":2,"metrics":{"LAS":"91.45","UAS":"93.60"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-partut","task":"Dependency Parsing","dataset":"ParTUT","model":"UDify","rank_in_archive_order":2,"of":2,"metrics":{"LAS":"88.06","UAS":"90.55"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-sequoia-treebank","task":"Dependency Parsing","dataset":"Sequoia Treebank","model":"UDify","rank_in_archive_order":2,"of":2,"metrics":{"LAS":"90.05","UAS":"92.53"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-spoken-corpus","task":"Dependency Parsing","dataset":"Spoken Corpus","model":"UDify","rank_in_archive_order":2,"of":2,"metrics":{"LAS":"80.01","UAS":"85.24"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-universal-dependencies","task":"Dependency Parsing","dataset":"Universal Dependencies","model":"UDify","rank_in_archive_order":2,"of":6,"metrics":{"LAS":"80.43","UAS":"85.69"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.02099","atlas_url":"https://app.syntology.ai/?focus=1904.02099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02099"}},"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/hyperparticle/udify","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ahmetustun/udapter","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idiap/g2g-transformer","reach":{"status":"ok","spdx":"GPL-2.0"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"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":"dd23f8f805a509d4","entry":"apply_lemma_rule","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/lemma_edit.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/lemma_edit.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":"dd23f8f805a509d4"}},{"code_sha256_prefix":"665f20ac94b4aa09","entry":"distance","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/evaluate_2019_task2.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/evaluate_2019_task2.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":"665f20ac94b4aa09"}},{"code_sha256_prefix":"245d8f594031798b","entry":"evaluate","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/conll18_ud_eval.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/conll18_ud_eval.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":"245d8f594031798b"}},{"code_sha256_prefix":"d56f4a572f75726c","entry":"gen_lemma_rule","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/lemma_edit.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/lemma_edit.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":"d56f4a572f75726c"}},{"code_sha256_prefix":"41be2131e0bb7615","entry":"get_ud_treebank_files","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/util.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/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":"41be2131e0bb7615"}},{"code_sha256_prefix":"e9c1c9c44d53c7dc","entry":"get_ud_treebank_names","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/util.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/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":"e9c1c9c44d53c7dc"}},{"code_sha256_prefix":"7db5fbed47b0c09d","entry":"load_conllu","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/conll18_ud_eval.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/conll18_ud_eval.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":"7db5fbed47b0c09d"}},{"code_sha256_prefix":"d6122a3c08a641ad","entry":"load_conllu_file","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/conll18_ud_eval.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/conll18_ud_eval.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":"d6122a3c08a641ad"}},{"code_sha256_prefix":"6b04a2e33ab50ab7","entry":"manipulate_data","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/evaluate_2019_task2.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/evaluate_2019_task2.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":"6b04a2e33ab50ab7"}},{"code_sha256_prefix":"277006db04b14f51","entry":"min_edit_script","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/lemma_edit.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/lemma_edit.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":"277006db04b14f51"}},{"code_sha256_prefix":"dff441cf8da0ff92","entry":"sequence_cross_entropy","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/models/tag_decoder.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/models/tag_decoder.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":"dff441cf8da0ff92"}},{"code_sha256_prefix":"f5cf6da83aa49097","entry":"set_equal","repo":"hyperparticle/udify","repo_kind":"official","path":"udify/dataset_readers/evaluate_2019_task2.py","file_url":"https://github.com/hyperparticle/udify/blob/HEAD/udify/dataset_readers/evaluate_2019_task2.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":"f5cf6da83aa49097"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}