{"url":"/sota/morpheme-segmentaiton-on-unimorph-4-0","task":{"name":"Morpheme Segmentaiton","url":"/task/morpheme-segmentaiton","note":null},"dataset":{"name":"UniMorph 4.0","url":"/dataset/unimorph"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Succesful systems segment a given word or sentence into a sequence of morphemes.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["macro avg (subtask 1)","f1 macro avg (subtask 2)","lev dist (subtask 2)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"macro avg (subtask 1)":null,"f1 macro avg (subtask 2)":"higher","lev dist (subtask 2)":null}},"counts":{"rows":19,"rows_with_code":7,"rows_with_paper_page":19,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Subword-ULM transformer (DeepSPIN-3; soft-attention, 1-5 entmax)","metrics":{"macro avg (subtask 1)":"97.29"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/beyond-characters-subword-level-morpheme","paper_url":"https://aclanthology.org/2022.sigmorphon-1.14","paper_title":"Beyond Characters: Subword-level Morpheme Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Char LSTM (DeepSPIN-2; soft-attention, 1-5 entmax)","metrics":{"macro avg (subtask 1)":"97.15"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/beyond-characters-subword-level-morpheme","paper_url":"https://aclanthology.org/2022.sigmorphon-1.14","paper_title":"Beyond Characters: Subword-level Morpheme Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Ensemble of hard-attention transducers (CLUZH)","metrics":{"macro avg (subtask 1)":"96.85"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/cluzh-at-sigmorphon-2022-shared-tasks-on","paper_url":"https://aclanthology.org/2022.sigmorphon-1.21","paper_title":"CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation","code":"https://github.com/slvnwhrl/il-reimplementation","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Char LSTM (DeepSPIN-1; soft-attention)","metrics":{"macro avg (subtask 1)":"96.32"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/beyond-characters-subword-level-morpheme","paper_url":"https://aclanthology.org/2022.sigmorphon-1.14","paper_title":"Beyond Characters: Subword-level Morpheme Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"BiLSTM for seq labelling (Tü_Seg-1)","metrics":{"macro avg (subtask 1)":"96.06"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/sigmorphon-2022-shared-task-on-morpheme","paper_url":"https://aclanthology.org/2022.sigmorphon-1.13","paper_title":"SIGMORPHON 2022 Shared Task on Morpheme Segmentation Submission Description: Sequence Labelling for Word-Level Morpheme Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Bidirectional GRU + Morfessor features (AUUH_F)","metrics":{"f1 macro avg (subtask 2)":"66.73","lev dist (subtask 2)":"36.35","macro avg (subtask 1)":"93.72"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"HMM (JB132; trained w EM)","metrics":{"macro avg (subtask 1)":"58.39"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/jb132-submission-to-the-sigmorphon-2022","paper_url":"https://aclanthology.org/2022.sigmorphon-1.17","paper_title":"JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Morfessor2","metrics":{"f1 macro avg (subtask 2)":"50.65","lev dist (subtask 2)":"12.08","macro avg (subtask 1)":"25.57"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/the-sigmorphon-2022-shared-task-on-morpheme","paper_url":"https://arxiv.org/abs/2206.07615v1","paper_title":"The SIGMORPHON 2022 Shared Task on Morpheme Segmentation","code":"https://github.com/sigmorphon/2022segmentationst","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"ULM","metrics":{"f1 macro avg (subtask 2)":"45.99","lev dist (subtask 2)":"14.28","macro avg (subtask 1)":"20.61"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/the-sigmorphon-2022-shared-task-on-morpheme","paper_url":"https://arxiv.org/abs/2206.07615v1","paper_title":"The SIGMORPHON 2022 Shared Task on Morpheme Segmentation","code":"https://github.com/sigmorphon/2022segmentationst","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"WordPiece","metrics":{"f1 macro avg (subtask 2)":"40.59","lev dist (subtask 2)":"17.54","macro avg (subtask 1)":"15.89"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/the-sigmorphon-2022-shared-task-on-morpheme","paper_url":"https://arxiv.org/abs/2206.07615v1","paper_title":"The SIGMORPHON 2022 Shared Task on Morpheme Segmentation","code":"https://github.com/sigmorphon/2022segmentationst","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"AUUH_B","metrics":{"f1 macro avg (subtask 2)":"89.77","lev dist (subtask 2)":"3.50"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"AUUH_A","metrics":{"f1 macro avg (subtask 2)":"89.00","lev dist (subtask 2)":"4.08"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"CLUZH-3","metrics":{"f1 macro avg (subtask 2)":"88.14","lev dist (subtask 2)":"5.58"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/cluzh-at-sigmorphon-2022-shared-tasks-on","paper_url":"https://aclanthology.org/2022.sigmorphon-1.21","paper_title":"CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation","code":"https://github.com/slvnwhrl/il-reimplementation","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"CLUZH-2","metrics":{"f1 macro avg (subtask 2)":"87.93","lev dist (subtask 2)":"5.62"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/cluzh-at-sigmorphon-2022-shared-tasks-on","paper_url":"https://aclanthology.org/2022.sigmorphon-1.21","paper_title":"CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation","code":"https://github.com/slvnwhrl/il-reimplementation","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CLUZH-1","metrics":{"f1 macro avg (subtask 2)":"87.68","lev dist (subtask 2)":"5.69"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/cluzh-at-sigmorphon-2022-shared-tasks-on","paper_url":"https://aclanthology.org/2022.sigmorphon-1.21","paper_title":"CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation","code":"https://github.com/slvnwhrl/il-reimplementation","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"BiLSTM for seq labelling (Tü_Seg-2)","metrics":{"f1 macro avg (subtask 2)":"82.07","lev dist (subtask 2)":"4.71"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/sigmorphon-2022-shared-task-on-morpheme","paper_url":"https://aclanthology.org/2022.sigmorphon-1.13","paper_title":"SIGMORPHON 2022 Shared Task on Morpheme Segmentation Submission Description: Sequence Labelling for Word-Level Morpheme Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"AUUH_E","metrics":{"f1 macro avg (subtask 2)":"73.21","lev dist (subtask 2)":"31.05"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"AUUH_D","metrics":{"f1 macro avg (subtask 2)":"72.75","lev dist (subtask 2)":"36.38"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"AUUH_C","metrics":{"f1 macro avg (subtask 2)":"70.76","lev dist (subtask 2)":"35.94"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/morfessor-enriched-features-and-multilingual","paper_url":"https://aclanthology.org/2022.sigmorphon-1.16","paper_title":"Morfessor-enriched features and multilingual training for canonical morphological segmentation","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}