{"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/papers/3","list_of":"/task/chinese-word-segmentation","task":"Chinese Word Segmentation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,244],"of":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"},"first_page":"/task/chinese-word-segmentation","prev":"/task/chinese-word-segmentation/papers/2","next":null,"papers":[{"url":null,"slug":"human-computer-interactive-chinese-word","title":"Human-Computer Interactive Chinese Word Segmentation: An Adaptive Dirichlet Process Mixture Model Approach","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-chinese-word-segmentation-and-pos","title":"Joint Chinese Word Segmentation and POS Tagging on Heterogeneous Annotated Corpora with Multiple Task Learning","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lattice-based-framework-for-joint-chinese","title":"A Lattice-based Framework for Joint Chinese Word Segmentation, POS Tagging and Parsing","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"co-regularizing-character-based-and-word","title":"Co-regularizing character-based and word-based models for semi-supervised Chinese word segmentation","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-learning-with-natural","title":"Discriminative Learning with Natural Annotations: Word Segmentation as a Case Study","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grammars-and-topic-models","title":"Grammars and Topic Models","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-semi-supervised-model-for-joint","title":"Graph-based Semi-Supervised Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-chinese-word-segmentation-on-micro","title":"Improving Chinese Word Segmentation on Micro-blog Using Rich Punctuations","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-informal-language-from-chinese","title":"Mining Informal Language from Chinese Microtext: Joint Word Recognition and Segmentation","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reduce-meaningless-words-for-joint-chinese","title":"Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging","date":"2013-05-25","arxiv_id":"1305.5918","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-tree-based-chinese-word-segmentation","title":"Binary Tree based Chinese Word Segmentation","date":"2013-05-17","arxiv_id":"1305.3981","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cascaded-approach-for-cips-sighan-micro","title":"A Cascaded Approach for CIPS-SIGHAN Micro-Blog Word Segmentation Bakeoff 2012","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-chinese-word-segmentation-on","title":"A Comparison of Chinese Word Segmentation on News and Microblog Corpora with a Lexicon Based Method","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mmsm-based-hybrid-method-for-chinese","title":"A MMSM-based Hybrid Method for Chinese MicroBlog Word Segmentation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-chinese-word-segmentation","title":"Active Learning for Chinese Word Segmentation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-conventional-chinese-word-segmenter","title":"Adapting Conventional Chinese Word Segmenter for Segmenting Micro-blog Text: Combining Rule-based and Statistic-based Approaches","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-chinese-weibo-segmentation-based-on","title":"Cascaded Chinese Weibo Segmentation Based on CRFs","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-tweets-segmentation-based-on","title":"Chinese Tweets Segmentation based on Morphemes","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crfs-based-chinese-word-segmentation-for","title":"CRFs-Based Chinese Word Segmentation for Micro-Blog with Small-Scale Data","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-boosting-from-dictionary-and","title":"Discriminative Boosting from Dictionary and Raw Text -- A Novel Approach to Build A Chinese Word Segmenter","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-based-training-data-selection-for","title":"Entropy-based Training Data Selection for Domain Adaptation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-maximum-pattern-matching-with","title":"Hierarchical Maximum Pattern Matching with Rule Induction Approach for Sentence Parsing","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-surface-and-abstract-features-for","title":"Integrating Surface and Abstract Features for Robust Cross-Domain Chinese Word Segmentation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-segmentation-and-tagging-with-coupled","title":"Joint Segmentation and Tagging with Coupled Sequences Labeling","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"micro-blogs-oriented-word-segmentation-system","title":"Micro blogs Oriented Word Segmentation System","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rules-based-chinese-word-segmentation-on","title":"Rules-based Chinese Word Segmentation on MicroBlog for CIPS-SIGHAN on CLP2012","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-automatic-annotation-of-chinese-word","title":"Semi-automatic Annotation of Chinese Word Structure","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-chinese-word-segmentation-for","title":"Semi-supervised Chinese Word Segmentation for CLP2012","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"soochow-university-word-segmenter-for-sighan","title":"Soochow University Word Segmenter for SIGHAN 2012 Bakeoff","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-cips-sighan-clp-2012-chineseword","title":"The CIPS-SIGHAN CLP 2012 ChineseWord Segmentation onMicroBlog Corpora Bakeoff","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-segmentation-on-chinese-mirco-blog-data","title":"Word Segmentation on Chinese Mirco-Blog Data with a Linear-Time Incremental Model","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-word-segmentation-be-considered-harmful","title":"Can Word Segmentation be Considered Harmful for Statistical Machine Translation Tasks between Japanese and Chinese?","date":"2012-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancement-of-feature-engineering-for","title":"Enhancement of Feature Engineering for Conditional Random Field Learning in Chinese Word Segmentation Using Unlabeled Data","date":"2012-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"strategies-of-processing-japanese-names-and","title":"Strategies of Processing Japanese Names and Character Variants in Traditional Chinese Text","date":"2012-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-statistical-machine-translation","title":"Enhancing Statistical Machine Translation with Character Alignment","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-deterministic-constraints-from-a","title":"Exploring Deterministic Constraints: from a Constrained English POS Tagger to an Efficient ILP Solution to Chinese Word Segmentation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-online-training-with-frequency-adaptive","title":"Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-annotation-transformation-with","title":"Iterative Annotation Transformation with Predict-Self Reestimation for Chinese Word Segmentation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-chinese-word-segmentation-pos-tagging","title":"Joint Chinese Word Segmentation, POS Tagging and Parsing","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-approximation-and-estimation-errors","title":"Reducing Approximation and Estimation Errors for Chinese Lexical Processing with Heterogeneous Annotations","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phrase-model-training-for-statistical-machine","title":"Phrase Model Training for Statistical Machine Translation with Word Lattices of Preprocessing Alternatives","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-non-supervisee-le-cas-du","title":"Segmentation non supervis\\'ee : le cas du mandarin (Unsupervized Word Segmentation) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-grammar-informed-corpus-based-sentence","title":"A Grammar-informed Corpus-based Sentence Database for Linguistic and Computational Studies","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-a-goodness-measurement-for-domain","title":"Using a Goodness Measurement for Domain Adaptation: A Case Study on Chinese Word Segmentation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"8956cbb97f46f2b3872642aca3f9d1258dcf44d0fcc4a65c4330bef79055177e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}