{"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/document-classification/papers/7","list_of":"/task/document-classification","task":"Document Classification","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":7,"pages_in_order":7,"rows_per_page":100,"rows":[601,641],"of":641,"counts":{"archive_papers_tagged":641,"with_a_code_link":235,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":641,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/document-classification","prev":"/task/document-classification/papers/6","next":null,"papers":[{"url":null,"slug":"automatic-construction-of-amharic-semantic","title":"Automatic Construction of Amharic Semantic Networks from Unstructured Text Using Amharic WordNet","date":"2014-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"documents-as-multiple-overlapping-windows","title":"Documents as multiple overlapping windows into grids of counts","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-similarity-using-constructions-as","title":"Word similarity using constructions as contextual features","date":"2013-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semidefinite-programming-based","title":"Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization","date":"2013-10-08","arxiv_id":"1310.2273","repositories_listed":0,"syntology":null},{"url":null,"slug":"centering-similarity-measures-to-reduce-hubs","title":"Centering Similarity Measures to Reduce Hubs","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-naive-bayes-classifier-for-document","title":"Semantic Na\\\"\\ive Bayes Classifier for Document Classification","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-representation-learning-for-1","title":"Semi-Supervised Representation Learning for Cross-Lingual Text Classification","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-crowdsourcing-to-get-representations","title":"Using Crowdsourcing to get Representations based on Regular Expressions","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"word-level-language-identification-in-online","title":"Word Level Language Identification in Online Multilingual Communication","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-documents-with-deep-boltzmann","title":"Modeling Documents with Deep Boltzmann Machines","date":"2013-09-26","arxiv_id":"1309.6865","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evaluation-summary-method-based-on-a","title":"An Evaluation Summary Method Based on a Combination of Content and Linguistic Metrics","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"more-than-bag-of-words-sentence-based","title":"More than Bag-of-Words: Sentence-based Document Representation for Sentiment Analysis","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-supervised-approach-for-natural","title":"A Semi-supervised Approach for Natural Language Call Routing","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-the-basics-of-nlp-and-ml-in-an","title":"Teaching the Basics of NLP and ML in an Introductory Course to Information Science","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-classification-for-historical","title":"Temporal classification for historical Romanian texts","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dropout-training-as-adaptive-regularization","title":"Dropout Training as Adaptive Regularization","date":"2013-07-04","arxiv_id":"1307.1493","repositories_listed":0,"syntology":null},{"url":null,"slug":"umbc_ebiquity-core-semantic-textual","title":"UMBC\\_EBIQUITY-CORE: Semantic Textual Similarity Systems","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-bregman-divergence-and-gradient","title":"Generalized Bregman Divergence and Gradient of Mutual Information for Vector Poisson Channels","date":"2013-01-28","arxiv_id":"1301.6648","repositories_listed":0,"syntology":null},{"url":null,"slug":"attribute-based-chinese-named-entity","title":"Attribute based Chinese Named Entity Recognition and Disambiguation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-interviews-a-case-study-on","title":"Classification of Interviews - A Case Study on Cancer Patients","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-inference-in-neural-circuits-with","title":"Complex Inference in Neural Circuits with Probabilistic Population Codes and Topic Models","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-discrimination-between-closely","title":"Efficient Discrimination Between Closely Related Languages","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inducing-crosslingual-distributed","title":"Inducing Crosslingual Distributed Representations of Words","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"keyphrase-extraction-in-scientific-articles-a","title":"Keyphrase Extraction in Scientific Articles: A Supervised Approach","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-arabic-wikipedia-into-the-named","title":"Mapping Arabic Wikipedia into the Named Entities Taxonomy","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-learning-in-random-subspaces-equipping","title":"Robust Learning in Random Subspaces: Equipping NLP for OOV Effects","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-modeling-based-domain-adaptation-for","title":"Topic Modeling-based Domain Adaptation for System Combination","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotation-scheme-for-constructing-sentiment","title":"Annotation Scheme for Constructing Sentiment Corpus in Korean","date":"2012-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-word-representations-via-global","title":"Improving Word Representations via Global Context and Multiple Word Prototypes","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-multi-view-domain","title":"Information-theoretic Multi-view Domain Adaptation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effacement-de-dimensions-de-similarite","title":"Effacement de dimensions de similarit\\'e textuelle pour l'exploration de collections de rapports d'incidents a\\'eronautiques (Deletion of dimensions of textual similarity for the exploration of collections of accident reports in aviation) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"taxonomy-induction-using-hierarchical-random","title":"Taxonomy Induction Using Hierarchical Random Graphs","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-divergence-measures-for-automated","title":"Assessing Divergence Measures for Automated Document Routing in an Adaptive MT System","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-sentiment-labels-for","title":"Bootstrapping Sentiment Labels For Unannotated Documents With Polarity PageRank","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"irregularity-detection-in-categorized","title":"Irregularity Detection in Categorized Document Corpora","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-resources-for-handwriting","title":"Linguistic Resources for Handwriting Recognition and Translation Evaluation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experiments-on-hybrid-corpus-based-sentiment","title":"Experiments on Hybrid Corpus-Based Sentiment Lexicon Acquisition","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"collective-classification-of-textual","title":"Collective Classification of Textual Documents by Guided Self-Organization in T-Cell Cross-Regulation Dynamics","date":"2011-02-04","arxiv_id":"1102.1027","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-optimization-for-discriminative","title":"Efficient Optimization for Discriminative Latent Class Models","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reverse-multi-label-learning","title":"Reverse Multi-Label Learning","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-naive-bayes-machine-learning","title":"A Survey of Naïve Bayes Machine Learning approach in Text Document Classification","date":"2010-03-09","arxiv_id":"1003.1795","repositories_listed":0,"syntology":null}],"record_sha256":"d2dda7b7e12d361d2b5fd79a7bb264c46a76c66aa278be12da3f237fccb91ed4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}