{"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":"/task/chinese-word-segmentation","name":"Chinese Word Segmentation","slug":"chinese-word-segmentation","description_markdown":"Chinese word segmentation is the task of splitting Chinese text (i.e. a sequence of Chinese characters) into words (Source: www.nlpprogress.com).","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":244,"papers_with_code":50,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/chinese-word-segmentation-on-msr","slug":"chinese-word-segmentation-on-msr","dataset":"MSR","dataset_url":null,"rows_in_archive":6,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"BABERT-LE","paper_title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","paper_url":"/paper/unsupervised-boundary-aware-language-model","paper_date":"2022-10-27","arxiv_id":"2210.15231","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/babert"}],"syntology":null}},{"leaderboard":"/sota/chinese-word-segmentation-on-ctb6","slug":"chinese-word-segmentation-on-ctb6","dataset":"CTB6","dataset_url":null,"rows_in_archive":4,"metrics":["F1"],"first_row_in_archive_order":{"model":"LATTE (Linguistic units, lattices, PTMs, GNNs)","paper_title":"LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation","paper_url":"/paper/latte-lattice-attentive-encoding-for","paper_date":"2023-06-01","arxiv_id":null,"code_links":[{"title":"tchayintr/latte-ptm-ws","url":"https://github.com/tchayintr/latte-ptm-ws"},{"title":"tchayintr/latte-ws","url":"https://github.com/tchayintr/latte-ws"}],"syntology":null}},{"leaderboard":"/sota/chinese-word-segmentation-on-pku","slug":"chinese-word-segmentation-on-pku","dataset":"PKU","dataset_url":null,"rows_in_archive":4,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"BABERT-LE","paper_title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","paper_url":"/paper/unsupervised-boundary-aware-language-model","paper_date":"2022-10-27","arxiv_id":"2210.15231","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/babert"}],"syntology":null}},{"leaderboard":"/sota/chinese-word-segmentation-on-msra","slug":"chinese-word-segmentation-on-msra","dataset":"MSRA","dataset_url":"/dataset/msra-cn-ner","rows_in_archive":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"BABERT-LE","paper_title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","paper_url":"/paper/unsupervised-boundary-aware-language-model","paper_date":"2022-10-27","arxiv_id":"2210.15231","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"modelscope/AdaSeq","url":"https://github.com/modelscope/AdaSeq/tree/master/examples/babert"}],"syntology":null}},{"leaderboard":"/sota/chinese-word-segmentation-on-as","slug":"chinese-word-segmentation-on-as","dataset":"AS","dataset_url":null,"rows_in_archive":2,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"Glyce + BERT","paper_title":"Glyce: Glyph-vectors for Chinese Character Representations","paper_url":"/paper/glyce-glyph-vectors-for-chinese-character","paper_date":"2019-01-29","arxiv_id":"1901.10125","code_links":[{"title":"ShannonAI/glyce","url":"https://github.com/ShannonAI/glyce"},{"title":"zhangyuwangumass/Glyph-based-Chinese-Character-Embedding","url":"https://github.com/zhangyuwangumass/Glyph-based-Chinese-Character-Embedding"}],"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/chinese-word-segmentation-on-cityu","slug":"chinese-word-segmentation-on-cityu","dataset":"CITYU","dataset_url":null,"rows_in_archive":2,"metrics":["F1","Precision","Recall"],"first_row_in_archive_order":{"model":"WMSeg + ZEN","paper_title":"Improving Chinese Word Segmentation with Wordhood Memory Networks","paper_url":"/paper/improving-chinese-word-segmentation-with","paper_date":"2020-07-01","arxiv_id":null,"code_links":[{"title":"SVAIGBA/WMSeg","url":"https://github.com/SVAIGBA/WMSeg"}],"syntology":null}}],"datasets":[{"url":"/dataset/msra-cn-ner","name":"MSRA CN NER","full_name":"MSRA CN NER Dataset","num_papers_in_archive":23},{"url":"/dataset/cuge","name":"CUGE","full_name":"","num_papers_in_archive":4},{"url":"/dataset/lsicc","name":"LSICC","full_name":"Large Scale Informal Chinese Corpus","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/chinese","name":"Chinese"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":244,"of_with_code":50,"tagged_in_all":244,"counts":{"archive_papers_tagged":244,"with_a_code_link":50,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":244,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/zen-pre-training-chinese-text-encoder","slug":"zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","arxiv_id":"1911.00720","repositories_listed":7,"syntology":{"n":35,"n_ran":28,"n_constructed":0,"n_ran_checked":22,"n_instrument":6,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":2,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/zen-pre-training-chinese-text-encoder#ran","syntology_url":"https://syntology.ai/paper/1911.00720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00720"}},"official":{"repos":["sinovation/ZEN"],"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"]}}},{"url":"/paper/pkuseg-a-toolkit-for-multi-domain-chinese","slug":"pkuseg-a-toolkit-for-multi-domain-chinese","title":"PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation","date":"2019-06-27","arxiv_id":"1906.11455","repositories_listed":4,"syntology":null},{"url":"/paper/simplifying-neural-machine-translation-with","slug":"simplifying-neural-machine-translation-with","title":"Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks","date":"2018-10-30","arxiv_id":"1810.12546","repositories_listed":3,"syntology":null},{"url":"/paper/latte-lattice-attentive-encoding-for","slug":"latte-lattice-attentive-encoding-for","title":"LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation","date":"2023-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-boundary-aware-language-model","slug":"unsupervised-boundary-aware-language-model","title":"Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling","date":"2022-10-27","arxiv_id":"2210.15231","repositories_listed":2,"syntology":null},{"url":"/paper/shuowen-jiezi-linguistically-informed","slug":"shuowen-jiezi-linguistically-informed","title":"Sub-Character Tokenization for Chinese Pretrained Language Models","date":"2021-06-01","arxiv_id":"2106.00400","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shuowen-jiezi-linguistically-informed#ran","syntology_url":"https://syntology.ai/paper/2106.00400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00400"}},"official":{"repos":["thunlp/subchartokenization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/investigating-self-attention-network-for","slug":"investigating-self-attention-network-for","title":"Investigating Self-Attention Network for Chinese Word Segmentation","date":"2019-07-26","arxiv_id":"1907.11512","repositories_listed":2,"syntology":null},{"url":"/paper/glyce-glyph-vectors-for-chinese-character","slug":"glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","arxiv_id":"1901.10125","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lsicc-a-large-scale-informal-chinese-corpus","slug":"lsicc-a-large-scale-informal-chinese-corpus","title":"LSICC: A Large Scale Informal Chinese Corpus","date":"2018-11-26","arxiv_id":"1811.10167","repositories_listed":2,"syntology":null},{"url":"/paper/segmental-recurrent-neural-networks","slug":"segmental-recurrent-neural-networks","title":"Segmental Recurrent Neural Networks","date":"2015-11-18","arxiv_id":"1511.06018","repositories_listed":2,"syntology":null},{"url":"/paper/mining-word-boundaries-from-speech-text","slug":"mining-word-boundaries-from-speech-text","title":"Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation","date":"2024-12-12","arxiv_id":"2412.09045","repositories_listed":1,"syntology":null},{"url":"/paper/legal-documents-drafting-with-fine-tuned-pre","slug":"legal-documents-drafting-with-fine-tuned-pre","title":"Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model","date":"2024-06-06","arxiv_id":"2406.04202","repositories_listed":1,"syntology":null},{"url":"/paper/the-uncertainty-based-retrieval-framework-for-1","slug":"the-uncertainty-based-retrieval-framework-for-1","title":"The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS","date":"2023-10-12","arxiv_id":"2310.08496","repositories_listed":1,"syntology":null},{"url":"/paper/ancient-chinese-word-segmentation-and-part-of-1","slug":"ancient-chinese-word-segmentation-and-part-of-1","title":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision","date":"2023-03-03","arxiv_id":"2303.01912","repositories_listed":1,"syntology":null},{"url":"/paper/gnn-sl-sequence-labeling-based-on-nearest","slug":"gnn-sl-sequence-labeling-based-on-nearest","title":"GNN-SL: Sequence Labeling Based on Nearest Examples via GNN","date":"2022-12-05","arxiv_id":"2212.02017","repositories_listed":1,"syntology":null},{"url":"/paper/chimst-a-chinese-medical-corpus-for-word","slug":"chimst-a-chinese-medical-corpus-for-word","title":"ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-chinese-word-segmentation-with-1","slug":"unsupervised-chinese-word-segmentation-with-1","title":"Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weighted-self-distillation-for-chinese-word","slug":"weighted-self-distillation-for-chinese-word","title":"Weighted self Distillation for Chinese word segmentation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/word-segmentation-by-separation-inference-for","slug":"word-segmentation-by-separation-inference-for","title":"Word Segmentation by Separation Inference for East Asian Languages","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-accurate-span-based-semantic-role","slug":"fast-and-accurate-span-based-semantic-role","title":"Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing","date":"2021-12-06","arxiv_id":"2112.02970","repositories_listed":1,"syntology":null},{"url":"/paper/more-than-text-multi-modal-chinese-word","slug":"more-than-text-multi-modal-chinese-word","title":"More than Text: Multi-modal Chinese Word Segmentation","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-word-segmentation-and-medical","slug":"exploring-word-segmentation-and-medical","title":"Exploring Word Segmentation and Medical Concept Recognition for Chinese Medical Texts","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/joint-chinese-word-segmentation-and-part-of-1","slug":"joint-chinese-word-segmentation-and-part-of-1","title":"Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-url-segmentation-with-1","slug":"semi-supervised-url-segmentation-with-1","title":"Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinkcws-is-chinese-word-segmentation-a","slug":"rethinkcws-is-chinese-word-segmentation-a","title":"RethinkCWS: Is Chinese Word Segmentation a Solved Task?","date":"2020-11-13","arxiv_id":"2011.06858","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-url-segmentation-with","slug":"semi-supervised-url-segmentation-with","title":"Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph Entities","date":"2020-11-05","arxiv_id":"2011.03138","repositories_listed":1,"syntology":null},{"url":"/paper/n-ltp-a-open-source-neural-chinese-language","slug":"n-ltp-a-open-source-neural-chinese-language","title":"N-LTP: An Open-source Neural Language Technology Platform for Chinese","date":"2020-09-24","arxiv_id":"2009.11616","repositories_listed":1,"syntology":null},{"url":"/paper/fasthan-a-bert-based-joint-many-task-toolkit","slug":"fasthan-a-bert-based-joint-many-task-toolkit","title":"fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP","date":"2020-09-18","arxiv_id":"2009.08633","repositories_listed":1,"syntology":null},{"url":"/paper/approaching-neural-chinese-word-segmentation","slug":"approaching-neural-chinese-word-segmentation","title":"Approaching Neural Chinese Word Segmentation as a Low-Resource Machine Translation Task","date":"2020-08-12","arxiv_id":"2008.05348","repositories_listed":1,"syntology":null},{"url":"/paper/coupling-distant-annotation-and-adversarial-1","slug":"coupling-distant-annotation-and-adversarial-1","title":"Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation","date":"2020-07-16","arxiv_id":"2007.08186","repositories_listed":1,"syntology":null},{"url":"/paper/improving-chinese-word-segmentation-with","slug":"improving-chinese-word-segmentation-with","title":"Improving Chinese Word Segmentation with Wordhood Memory Networks","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/joint-chinese-word-segmentation-and-part-of","slug":"joint-chinese-word-segmentation-and-part-of","title":"Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-chinese-word-segmentation-as-sequence","slug":"neural-chinese-word-segmentation-as-sequence","title":"Neural Chinese Word Segmentation as Sequence to Sequence Translation","date":"2019-11-29","arxiv_id":"1911.12982","repositories_listed":1,"syntology":null},{"url":"/paper/attention-is-all-you-need-for-chinese-word","slug":"attention-is-all-you-need-for-chinese-word","title":"Attention Is All You Need for Chinese Word Segmentation","date":"2019-10-31","arxiv_id":"1910.14537","repositories_listed":1,"syntology":null},{"url":"/paper/multi-criteria-chinese-word-segmentation-with","slug":"multi-criteria-chinese-word-segmentation-with","title":"A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder","date":"2019-06-28","arxiv_id":"1906.12035","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-model-for-joint-chinese-word","slug":"a-unified-model-for-joint-chinese-word","title":"A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing","date":"2019-04-09","arxiv_id":"1904.04697","repositories_listed":1,"syntology":null},{"url":"/paper/improving-cross-domain-chinese-word","slug":"improving-cross-domain-chinese-word","title":"Improving Cross-Domain Chinese Word Segmentation with Word Embeddings","date":"2019-03-05","arxiv_id":"1903.01698","repositories_listed":1,"syntology":null},{"url":"/paper/subword-encoding-in-lattice-lstm-for-chinese","slug":"subword-encoding-in-lattice-lstm-for-chinese","title":"Subword Encoding in Lattice LSTM for Chinese Word Segmentation","date":"2018-10-30","arxiv_id":"1810.12594","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-neural-word-segmentation-for","slug":"unsupervised-neural-word-segmentation-for","title":"Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling","date":"2018-10-07","arxiv_id":"1810.03167","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-transfer-learning-for-chinese","slug":"adversarial-transfer-learning-for-chinese","title":"Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/state-of-the-art-chinese-word-segmentation","slug":"state-of-the-art-chinese-word-segmentation","title":"State-of-the-art Chinese Word Segmentation with Bi-LSTMs","date":"2018-08-20","arxiv_id":"1808.06511","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-multi-task-transfer-learning-for","slug":"adaptive-multi-task-transfer-learning-for","title":"Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dual-long-short-term-memory-networks-for-sub","slug":"dual-long-short-term-memory-networks-for-sub","title":"Dual Long Short-Term Memory Networks for Sub-Character Representation Learning","date":"2017-12-23","arxiv_id":"1712.08841","repositories_listed":1,"syntology":null},{"url":"/paper/effective-neural-solution-for-multi-criteria","slug":"effective-neural-solution-for-multi-criteria","title":"Effective Neural Solution for Multi-Criteria Word Segmentation","date":"2017-12-07","arxiv_id":"1712.02856","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-neural-network-with-word","slug":"convolutional-neural-network-with-word","title":"Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation","date":"2017-11-13","arxiv_id":"1711.04411","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-accurate-neural-word-segmentation","slug":"fast-and-accurate-neural-word-segmentation","title":"Fast and Accurate Neural Word Segmentation for Chinese","date":"2017-04-24","arxiv_id":"1704.07047","repositories_listed":1,"syntology":null},{"url":"/paper/transition-based-neural-word-segmentation","slug":"transition-based-neural-word-segmentation","title":"Transition-Based Neural Word Segmentation","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-word-segmentation-learning-for-chinese","slug":"neural-word-segmentation-learning-for-chinese","title":"Neural Word Segmentation Learning for Chinese","date":"2016-06-14","arxiv_id":"1606.04300","repositories_listed":1,"syntology":null},{"url":"/paper/a-segmentation-matrix-method-for-chinese","slug":"a-segmentation-matrix-method-for-chinese","title":"A Segmentation Matrix Method for Chinese Segmentation Ambiguity Analysis","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-segment-representations-for-neural","slug":"exploring-segment-representations-for-neural","title":"Exploring Segment Representations for Neural Segmentation Models","date":"2016-04-19","arxiv_id":"1604.05499","repositories_listed":1,"syntology":null},{"url":null,"slug":"parsing-through-boundaries-in-chinese-word","title":"Parsing Through Boundaries in Chinese Word Segmentation","date":"2025-03-29","arxiv_id":"2503.23091","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-incorporating-heterogeneous","title":"An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling","date":"2024-02-21","arxiv_id":"2402.13534","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-deep-syntactic-and-semantic","title":"Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCN","date":"2023-06-03","arxiv_id":"2306.02078","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-chinese-word-segmentation-and-span","title":"Joint Chinese Word Segmentation and Span-based Constituency Parsing","date":"2022-11-03","arxiv_id":"2211.01638","repositories_listed":0,"syntology":null},{"url":null,"slug":"multifaceted-assessments-of-traditional","title":"Multifaceted Assessments of Traditional Chinese Word Segmentation Tool on Large Corpora","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-word-boundaries-in-speech-as-naturally","title":"Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data","date":"2022-10-31","arxiv_id":"2210.17122","repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-shen-jing-wang-luo-de-ban-jian-du","title":"基于神经网络的半监督CRF中文分词(Semi-supervised CRF Chinese Word Segmentation based on Neural Network)","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"that-slepen-al-the-nyght-with-open-ye-cross-2","title":"That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory","date":"2022-09-07","arxiv_id":"2209.02967","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-framework-for-ancient-chinese-ws-and","title":"A Joint Framework for Ancient Chinese WS and POS Tagging Based on Adversarial Ensemble Learning","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ancient-chinese-word-segmentation-and-part-of","title":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Data Augmentation","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-4ever-evahan-2022-ancient-chinese-word","title":"BERT 4EVER@EvaHan 2022: Ancient Chinese Word Segmentation and Part-of-Speech Tagging Based on Adversarial Learning and Continual Pre-training","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-first-international-ancient-chinese-word","title":"The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-evaluation-method-evaluation-data-and","title":"A New Evaluation Method: Evaluation Data and Metrics for Chinese Grammar Error Correction","date":"2022-04-30","arxiv_id":"2205.00217","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-word-segmentation-with-heterogeneous","title":"Chinese Word Segmentation with Heterogeneous Graph Neural Network","date":"2022-01-22","arxiv_id":"2201.08975","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-chinese-word-segmentation-and-part-of-2","title":"Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-stage Span Labeling","date":"2021-12-17","arxiv_id":"2112.09488","repositories_listed":0,"syntology":null},{"url":null,"slug":"green-cws-extreme-distillation-and-efficient-1","title":"Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application","date":"2021-11-17","arxiv_id":"2111.09078","repositories_listed":0,"syntology":null},{"url":null,"slug":"that-slepen-al-the-nyght-with-open-ye-cross","title":"That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-chinese-word-segmentation-with","title":"Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-prosody-for-unseen-texts-in-speech","title":"Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data","date":"2021-11-15","arxiv_id":"2111.07549","repositories_listed":0,"syntology":null},{"url":null,"slug":"lexicon-based-graph-convolutional-network-for","title":"Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-mask-and-predict-augmenting-chinese","title":"Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"span-labeling-approach-for-vietnamese-and","title":"Span Labeling Approach for Vietnamese and Chinese Word Segmentation","date":"2021-10-01","arxiv_id":"2110.00156","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-chinese-word-segmentation-via","title":"Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-chinese-word-segmentation-with","title":"Federated Chinese Word Segmentation with Global Character Associations","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-shuang-bian-ma-qi-de-yi-xue-wen-ben","title":"基于双编码器的医学文本中文分词(Chinese word segmentation of medical text based on dual-encoder)","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mvp-bert-multi-vocab-pre-training-for-chinese","title":"MVP-BERT: Multi-Vocab Pre-training for Chinese BERT","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-lstm-crf-attention-based-model","title":"Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation","date":"2021-05-20","arxiv_id":"2105.09681","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-more-efficient-chinese-named-entity","title":"A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis","date":"2021-01-11","arxiv_id":"2101.11423","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmenting-natural-language-sentences-via-1","title":"Segmenting Natural Language Sentences via Lexical Unit Analysis","date":"2020-12-10","arxiv_id":"2012.05418","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-word-segmentation-for-chinese","title":"Context-Aware Word Segmentation for Chinese Real-World Discourse","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-grained-chinese-word-segmentation-with","title":"Multi-grained Chinese Word Segmentation with Weakly Labeled Data","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fast-and-accurate-neural-chinese-word","title":"Towards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mvp-bert-redesigning-vocabularies-for-chinese-1","title":"MVP-BERT: Redesigning Vocabularies for Chinese BERT and Multi-Vocab Pretraining","date":"2020-11-17","arxiv_id":"2011.08539","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-multiple-criteria-model-in-transfer","title":"A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-model-for-chinese-word","title":"Pre-training with Meta Learning for Chinese Word Segmentation","date":"2020-10-23","arxiv_id":"2010.12272","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-for-graph-based-chinese","title":"A Joint Model for Graph-based Chinese Dependency Parsing","date":"2020-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-graph-matching-networks-for-chinese","title":"Neural Graph Matching Networks for Chinese Short Text Matching","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-uncertain-segmentation","title":"Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text","date":"2020-04-14","arxiv_id":"2004.06384","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-multi-criteria-chinese-word","title":"Unified Multi-Criteria Chinese Word Segmentation with BERT","date":"2020-04-13","arxiv_id":"2004.05808","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-boundary-assembling-into-a-dnn","title":"Integrating Boundary Assembling into a DNN Framework for Named Entity Recognition in Chinese Social Media Text","date":"2020-02-27","arxiv_id":"2002.11910","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-clustering-neural-network-for-chinese","title":"A New Clustering neural network for Chinese word segmentation","date":"2020-02-18","arxiv_id":"2002.07458","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-chinese-word-segmentation-1","title":"NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs","date":"2019-08-22","arxiv_id":"1908.08419","repositories_listed":0,"syntology":null},{"url":null,"slug":"shrinking-japanese-morphological-analyzers","title":"Shrinking Japanese Morphological Analyzers With Neural Networks and Semi-supervised Learning","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-realistic-and-robust-model-for-chinese-word","title":"A realistic and robust model for Chinese word segmentation","date":"2019-05-21","arxiv_id":"1905.08732","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-seq-to-seq-transformer-premised-temporal","title":"A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation","date":"2019-05-21","arxiv_id":"1905.08454","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-word-segmentation-necessary-for-deep","title":"Is Word Segmentation Necessary for Deep Learning of Chinese Representations?","date":"2019-05-14","arxiv_id":"1905.05526","repositories_listed":0,"syntology":null},{"url":null,"slug":"190501963","title":"Neural Chinese Word Segmentation with Lexicon and Unlabeled Data via Posterior Regularization","date":"2019-04-26","arxiv_id":"1905.01963","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-fast-and-accurate-neural-chinese-word","title":"Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning","date":"2019-03-11","arxiv_id":"1903.04190","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-word-segmentation-another-decade","title":"Chinese Word Segmentation: Another Decade Review (2007-2017)","date":"2019-01-18","arxiv_id":"1901.06079","repositories_listed":0,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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_where_code_ran":3,"papers_where_code_ran_first_page":"/task/chinese-word-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/chinese-word-segmentation/papers/2","json":"/task/chinese-word-segmentation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/chinese-word-segmentation/papers/3","json":"/task/chinese-word-segmentation/papers/3.json","rows":44},{"order":"ran","page":1,"of":1,"url":"/task/chinese-word-segmentation/papers/ran/1","json":"/task/chinese-word-segmentation/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"3850ae7e55e3843a47c0086ea0773daf3e38aaaf8aa729382e2afea2fee2fa68","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}