{"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/text-classification-1/papers/31","list_of":"/task/text-classification-1","task":"text-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":31,"pages_in_order":31,"rows_per_page":100,"rows":[3001,3054],"of":3054,"counts":{"archive_papers_tagged":3054,"with_a_code_link":1083,"where_syntology_ran_a_sample":204,"not_listed_spam_title":0,"listed":3054,"listed_where_code_ran":204,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":161,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":161,"listed_every_run_a_failure_of_syntologys_instrument":43,"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/text-classification-1","prev":"/task/text-classification-1/papers/30","next":null,"papers":[{"url":"/paper/lshtc-a-benchmark-for-large-scale-text","slug":"lshtc-a-benchmark-for-large-scale-text","title":"LSHTC: A Benchmark for Large-Scale Text Classification","date":"2015-03-30","arxiv_id":"1503.08581","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustly-leveraging-prior-knowledge-in-text","title":"Robustly Leveraging Prior Knowledge in Text Classification","date":"2015-03-03","arxiv_id":"1503.00841","repositories_listed":0,"syntology":null},{"url":null,"slug":"utility-theoretic-ranking-for-semi-automated","title":"Utility-Theoretic Ranking for Semi-Automated Text Classification","date":"2015-03-02","arxiv_id":"1503.00491","repositories_listed":0,"syntology":null},{"url":null,"slug":"rational-kernels-for-arabic-stemming-and-text","title":"Rational Kernels for Arabic Stemming and Text Classification","date":"2015-02-26","arxiv_id":"1502.07504","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-support-measure-machines-for-bag-of","title":"Latent Support Measure Machines for Bag-of-Words Data Classification","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-temporal-based-term-selection","title":"The Effect of Temporal-based Term Selection for Text Classification","date":"2014-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-language-text-classification-using","title":"Arabic Language Text Classification Using Dependency Syntax-Based Feature Selection","date":"2014-10-17","arxiv_id":"1410.4863","repositories_listed":0,"syntology":null},{"url":null,"slug":"corpora-preparation-and-stopword-list","title":"Corpora Preparation and Stopword List Generation for Arabic data in Social Network","date":"2014-10-05","arxiv_id":"1410.1135","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-discriminative-em","title":"Stochastic Discriminative EM","date":"2014-10-02","arxiv_id":"1410.1784","repositories_listed":0,"syntology":null},{"url":null,"slug":"term-weighting-learning-via-genetic","title":"Term-Weighting Learning via Genetic Programming for Text Classification","date":"2014-10-02","arxiv_id":"1410.0640","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-classification-for-natural","title":"Semi-supervised Classification for Natural Language Processing","date":"2014-09-25","arxiv_id":"1409.7612","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-using-association-rules","title":"Text Classification Using Association Rules, Dependency Pruning and Hyperonymization","date":"2014-07-28","arxiv_id":"1407.7357","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-phrase-structure-learning-methods","title":"A survey on phrase structure learning methods for text classification","date":"2014-06-21","arxiv_id":"1406.5598","repositories_listed":0,"syntology":null},{"url":null,"slug":"notes-on-hierarchical-ensemble-methods-for","title":"Notes on hierarchical ensemble methods for DAG-structured taxonomies","date":"2014-06-17","arxiv_id":"1406.4472","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-approach-for-text-and","title":"Machine learning approach for text and document mining","date":"2014-06-06","arxiv_id":"1406.1580","repositories_listed":0,"syntology":null},{"url":null,"slug":"sprinkling-topics-for-weakly-supervised-text","title":"Sprinkling Topics for Weakly Supervised Text Classification","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"new-perspectives-in-sinographic-language","title":"New Perspectives in Sinographic Language Processing Through the Use of Character Structure","date":"2014-05-21","arxiv_id":"1405.5474","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-parallel-way-to-select-the-parameters-of","title":"A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm","date":"2014-05-19","arxiv_id":"1405.4589","repositories_listed":0,"syntology":null},{"url":null,"slug":"thematically-reinforced-explicit-semantic","title":"Thematically Reinforced Explicit Semantic Analysis","date":"2014-05-17","arxiv_id":"1405.4364","repositories_listed":0,"syntology":null},{"url":null,"slug":"credibility-adjusted-term-frequency-a","title":"Credibility Adjusted Term Frequency: A Supervised Term Weighting Scheme for Sentiment Analysis and Text Classification","date":"2014-05-14","arxiv_id":"1405.3518","repositories_listed":0,"syntology":null},{"url":"/paper/kaggle-lshtc4-winning-solution","slug":"kaggle-lshtc4-winning-solution","title":"Kaggle LSHTC4 Winning Solution","date":"2014-05-03","arxiv_id":"1405.0546","repositories_listed":0,"syntology":null},{"url":null,"slug":"priors-for-random-count-matrices-derived-from","title":"Priors for Random Count Matrices Derived from a Family of Negative Binomial Processes","date":"2014-04-12","arxiv_id":"1404.3331","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-machine-learning","title":"A Comparative Study of Machine Learning Methods for Verbal Autopsy Text Classification","date":"2014-02-18","arxiv_id":"1402.4380","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-evaluation-of-machine-learning-1","title":"Performance Evaluation of Machine Learning Classifiers in Sentiment Mining","date":"2014-02-17","arxiv_id":"1402.3891","repositories_listed":0,"syntology":null},{"url":null,"slug":"cause-identification-from-aviation-safety","title":"Cause Identification from Aviation Safety Incident Reports via Weakly Supervised Semantic Lexicon Construction","date":"2014-01-16","arxiv_id":"1401.4436","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-multistage-of-multiple-classifiers-for","title":"Co-Multistage of Multiple Classifiers for Imbalanced Multiclass Learning","date":"2013-12-23","arxiv_id":"1312.6597","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-multi-label-text-classification","title":"Large-scale Multi-label Text Classification - Revisiting Neural Networks","date":"2013-12-19","arxiv_id":"1312.5419","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-probabilistic-hypotheses","title":"Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-ratio-matching-of-rbms-for-sparse","title":"Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-for-authorship","title":"Text Classification For Authorship Attribution Analysis","date":"2013-10-18","arxiv_id":"1310.4909","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-corpora-construction-for-text","title":"Automatic Corpora Construction for Text Classification","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-short-text-classification-based-on","title":"Chinese Short Text Classification Based on Domain Knowledge","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"global-model-for-hierarchical-multi-label","title":"Global Model for Hierarchical Multi-Label Text 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":"performance-investigation-of-feature","title":"Performance Investigation of Feature Selection Methods","date":"2013-09-16","arxiv_id":"1309.3949","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-text-classification-for-romanian","title":"Temporal Text Classification for Romanian Novels set in the Past","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reference-distance-estimator","title":"Reference Distance Estimator","date":"2013-08-18","arxiv_id":"1308.3818","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-contribution-of-unlabeled-data","title":"Exploring The Contribution of Unlabeled Data in Financial Sentiment Analysis","date":"2013-08-03","arxiv_id":"1308.0658","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-and-implicit-syntactic-features-for","title":"Explicit and Implicit Syntactic Features for Text Classification","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-based-on-the-latent","title":"Text Classification based on the Latent Topics of Important Sentences extracted by the PageRank Algorithm","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-from-positive-and","title":"Text Classification from Positive and Unlabeled Data using Misclassified Data Correction","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-approximate-aib-algorithm-for","title":"A Fast Approximate AIB Algorithm for Distributional Word Clustering","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extension-of-tsvm-to-multi-class-and","title":"Extension of TSVM to Multi-Class and Hierarchical Text Classification Problems With General Losses","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-tongues-lost-and-found-resources-and","title":"Native Tongues, Lost and Found: Resources and Empirical Evaluations in Native Language Identification","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-k-nearest-neighbor-efficacy-for","title":"Improving K-Nearest Neighbor Efficacy for Farsi Text Classification","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-feature-selection-method-for-multivariate","title":"A Feature Selection Method for Multivariate Performance Measures","date":"2011-03-05","arxiv_id":"1103.1013","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":"universal-kernels-on-non-standard-input","title":"Universal Kernels on Non-Standard Input Spaces","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dirichlet-bernoulli-alignment-a-generative","title":"Dirichlet-Bernoulli Alignment: A Generative Model for Multi-Class Multi-Label Multi-Instance Corpora","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-social-annotation-data-with-content","title":"Modeling Social Annotation Data with Content Relevance using a Topic Model","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-semantic-correlation-an","title":"Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text","date":"2008-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-learning-with-networks-of","title":"Regularized Learning with Networks of Features","date":"2008-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-randomized-algorithm-for-large-scale","title":"A Randomized Algorithm for Large Scale Support Vector Learning","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-instance-active-learning","title":"Multiple-Instance Active Learning","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"de47217f0283e54e76810419b5ed77de454255a3d657335dd4eb5d0a7d07abe9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}