{"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/papers/36","list_of":"/task/text-classification","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":36,"pages_in_order":37,"rows_per_page":100,"rows":[3501,3600],"of":3635,"counts":{"archive_papers_tagged":3635,"with_a_code_link":1308,"where_syntology_ran_a_sample":272,"not_listed_spam_title":0,"listed":3635,"listed_where_code_ran":272,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":219,"every_run_a_failure_of_syntologys_instrument":53,"listed_with_a_run_with_no_instrument_failure":219,"listed_every_run_a_failure_of_syntologys_instrument":53,"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","prev":"/task/text-classification/papers/35","next":"/task/text-classification/papers/37","papers":[{"url":null,"slug":"clips-stylometry-investigation-csi-corpus-a","title":"CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"collexen-automatically-generating-and","title":"ColLex.en: Automatically Generating and Evaluating a Full-form Lexicon for English","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-language-authorship-attribution","title":"Cross-Language Authorship Attribution","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-mining-with-shallow-vs-linguistic","title":"Data Mining with Shallow vs. Linguistic Features to Study Diversification of Scientific Registers","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-different-strategies-for-domain","title":"Evaluation of different strategies for domain adaptation in opinion mining","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hfst-swener-a-new-ner-resource-for-swedish","title":"HFST-SweNER --- A New NER Resource for Swedish","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hot-topics-and-schisms-in-nlp-community-and","title":"Hot Topics and Schisms in NLP: Community and Trend Analysis with Saffron on ACL and LREC Proceedings","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"named-entity-tagging-a-very-large-unbalanced","title":"Named Entity Tagging a Very Large Unbalanced Corpus: Training and Evaluating NE Classifiers","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-using-large-1","title":"Native Language Identification Using Large, Longitudinal Data","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-stopwords-filtering-and-data-sparsity-for","title":"On Stopwords, Filtering and Data Sparsity for Sentiment Analysis of Twitter","date":"2014-05-01","arxiv_id":null,"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":"deterministic-word-segmentation-using-maximum","title":"Deterministic Word Segmentation Using Maximum Matching with Fully Lexicalized Rules","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-text-ranking-and-automatic-dating-of","title":"Temporal Text Ranking and Automatic Dating of Texts","date":"2014-04-01","arxiv_id":null,"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":"classifying-english-documents-by-national","title":"Classifying English Documents by National Dialect","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-the-2013-alta-shared-task","title":"Overview of the 2013 ALTA Shared Task","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":"comparative-analyses-of-textual-contents-and","title":"Comparative Analyses of Textual Contents and Styles of Five Major Japanese Newspapers","date":"2013-11-01","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":"a-distant-supervision-approach-for","title":"A Distant Supervision Approach for Identifying Perspectives in Unstructured User-Generated Text","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-semantics-aware-distributional","title":"A Hierarchical Semantics-Aware Distributional Similarity Scheme","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-temporal-model-of-text-periodicities-using","title":"A temporal model of text periodicities using Gaussian Processes","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-two-stage-classifier-for-sentiment-analysis","title":"A Two-Stage Classifier for Sentiment Analysis","date":"2013-10-01","arxiv_id":null,"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":"building-the-chinese-open-wordnet-cow","title":"Building the Chinese Open Wordnet (COW): Starting from Core Synsets","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":"classifying-message-board-posts-with-an","title":"Classifying Message Board Posts with an Extracted Lexicon of Patient Attributes","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-noising-for-log-linear-structured","title":"Feature Noising for Log-Linear Structured Prediction","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-selection-using-a-semantic-hierarchy","title":"Feature Selection Using a Semantic Hierarchy for Event Recognition and Type Classification","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":"learning-latent-word-representations-for","title":"Learning Latent Word Representations for Domain Adaptation using Supervised Word Clustering","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":"sentiment-aggregation-using-conceptnet","title":"Sentiment Aggregation using ConceptNet Ontology","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"this-text-has-the-scent-of-starbucks-a","title":"This Text Has the Scent of Starbucks: A Laplacian Structured Sparsity Model for Computational Branding Analytics","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":"a-boosting-based-algorithm-for-classification","title":"A Boosting-based Algorithm for Classification of Semi-Structured Text using the Frequency of Substructures","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-symbolic-learning-can-help-statistical","title":"How Symbolic Learning Can Help Statistical Learning (and vice versa)","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-profiling-of-texts-across-textual","title":"Linguistic Profiling of Texts Across Textual Genres and Readability Levels. An Exploratory Study on Italian Fictional Prose","date":"2013-09-01","arxiv_id":null,"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":"towards-basque-oral-poetry-analysis-a-machine","title":"Towards Basque Oral Poetry Analysis: A Machine Learning Approach","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":"a-modular-open-source-focused-crawler-for","title":"A modular open-source focused crawler for mining monolingual and bilingual corpora from the web","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"categorization-of-turkish-news-documents-with","title":"Categorization of Turkish News Documents with Morphological Analysis","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-network-syntax-from-dependency","title":"Dependency Network Syntax: From Dependency Treebanks to a Classification of Chinese Function Words","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-training-and-dual-prediction-for","title":"Dual Training and Dual Prediction for Polarity Classification","date":"2013-08-01","arxiv_id":null,"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":"identification-of-patients-with-acute-lung","title":"Identification of Patients with Acute Lung Injury from Free-Text Chest X-Ray Reports","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-semantic-matching-application-to-cross","title":"Latent Semantic Matching: Application to Cross-language Text Categorization without Alignment Information","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-dbn-for-predicting-high-quality","title":"Multimodal DBN for Predicting High-Quality Answers in cQA portals","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-semi-supervised-naive-bayes-with","title":"Scaling Semi-supervised Naive Bayes with Feature Marginals","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-model-learning-with-feature","title":"Supervised Model Learning with Feature Grouping based on a Discrete Constraint","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":"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":"the-impact-of-topic-bias-on-quality-flaw","title":"The Impact of Topic Bias on Quality Flaw Prediction in Wikipedia","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-modeling-based-classification-of","title":"Topic Modeling Based Classification of Clinical Reports","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-tool-for-interactive-concept","title":"Towards a Tool for Interactive Concept Building for Large Scale Analysis in the Humanities","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-state-of-the-art-parsers-to","title":"Utilizing State-of-the-art Parsers to Diagnose Problems in Treebank Annotation for a Less Resourced Language","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":"cpn-core-a-text-semantic-similarity-system","title":"CPN-CORE: A Text Semantic Similarity System Infused with Opinion Knowledge","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-the-l1-of-non-native-writers-the","title":"Identifying the L1 of non-native writers: the CMU-Haifa system","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"labeling-the-languages-of-words-in-mixed","title":"Labeling the Languages of Words in Mixed-Language Documents using Weakly Supervised Methods","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-profiling-based-on-generalpurpose","title":"Linguistic Profiling based on General--purpose Features and Native Language Identification","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-with-ppm","title":"Native Language Identification with PPM","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nilc_usp-a-hybrid-system-for-sentiment","title":"NILC\\_USP: A Hybrid System for Sentiment Analysis in Twitter Messages","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recognition-of-classical-arabic-poems","title":"Recognition of Classical Arabic Poems","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-english-learners-native-language","title":"Recognizing English Learners' Native Language from Their Writings","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-annotation-effort-on-unbalanced","title":"Reducing Annotation Effort on Unbalanced Corpus based on Cost Matrix","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-classification-using-rough-set","title":"Sentiment Classification using Rough Set based Hybrid Feature Selection","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ucam-core-incorporating-structured","title":"UCAM-CORE: Incorporating structured distributional similarity into STS","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-pu-learning-to-detect-deceptive-opinion","title":"Using PU-Learning to Detect Deceptive Opinion Spam","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vtex-system-description-for-the-nli-2013","title":"VTEX System Description for the NLI 2013 Shared Task","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-an-unsupervised-approach-for","title":"Bootstrapping an Unsupervised Approach for Classifying Agreement and Disagreement","date":"2013-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evaluation-of-the-brazilian-portuguese","title":"An Evaluation of the Brazilian Portuguese LIWC Dictionary for Sentiment Analysis","date":"2013-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-supervised-bayesian-network-model-for","title":"A Semi-Supervised Bayesian Network Model for Microblog Topic Classification","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"affect-detection-from-semantic-interpretation","title":"Affect Detection from Semantic Interpretation of Drama Improvisation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-detection-of-psychological-distress","title":"Automatic Detection of Psychological Distress Indicators and Severity Assessment from Online Forum Posts","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-different-criteria-for-vietnamese","title":"Comparing Different Criteria for Vietnamese Word Segmentation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diachronic-variation-in-grammatical-relations","title":"Diachronic Variation in Grammatical Relations","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-based-classification-of-punjabi-text","title":"Domain Based Classification of Punjabi Text Documents using Ontology and Hybrid Based Approach","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-based-classification-of-punjabi-text-1","title":"Domain Based Classification of Punjabi Text Documents","date":"2012-12-01","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":"finding-thoughtful-comments-from-social-media","title":"Finding Thoughtful Comments from Social Media","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"native-language-identification-using","title":"Native Language Identification using Recurring $n$-grams -- Investigating Abstraction and Domain Dependence","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":"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":"sejfek-a-lexicon-and-a-shallow-grammar-of","title":"SEJFEK - a Lexicon and a Shallow Grammar of Polish Economic Multi-Word Units","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-of-naive-bayes","title":"Semi-supervised Learning of Naive Bayes Classifier with feature constraints","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-the-automatic-detection-of-the-source","title":"Towards the Automatic Detection of the Source Language of a Literary Translation.","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-collocation-segmentation-to-the-acl","title":"Applying Collocation Segmentation to the ACL Anthology Reference Corpus","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"baselines-and-bigrams-simple-good-sentiment","title":"Baselines and Bigrams: Simple, Good Sentiment and Topic Classification","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-adaptor-grammars-for-native","title":"Exploring Adaptor Grammars for Native Language Identification","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-semi-supervised-learning","title":"Graph-based Semi-Supervised Learning Algorithms for NLP","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"takelab-systems-for-measuring-semantic-text","title":"TakeLab: Systems for Measuring Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"6d0ef81065e3697fd76690093d02227b5ff5d10f52c4898dd5350e9d4b4d797b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}