{"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/named-entity-recognition-ner/papers/29","list_of":"/task/named-entity-recognition-ner","task":"Named Entity Recognition (NER)","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":29,"pages_in_order":29,"rows_per_page":100,"rows":[2801,2874],"of":2874,"counts":{"archive_papers_tagged":2874,"with_a_code_link":955,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":2874,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/named-entity-recognition-ner","prev":"/task/named-entity-recognition-ner/papers/28","next":null,"papers":[{"url":null,"slug":"automatically-generated-ne-tagged-corpora-for","title":"Automatically generated NE tagged corpora for English and Hungarian","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-trainable-taggers-in-a-web-based","title":"Building Trainable Taggers in a Web-based, UIMA-Supported NLP Workbench","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"celi-an-experiment-with-cross-language","title":"CELI: An Experiment with Cross Language Textual Entailment","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"character-level-machine-translation","title":"Character-Level Machine Translation Evaluation for Languages with Ambiguous Word Boundaries","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-nlp-without-magic","title":"Deep Learning for NLP (without Magic)","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eager-extending-automatically-gazetteers-for","title":"EAGER: Extending Automatically Gazetteers for Entity Recognition","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"illinois-coref-the-ui-system-in-the-conll","title":"Illinois-Coref: The UI System in the CoNLL-2012 Shared Task","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-nlp-through-marginalization-of","title":"Improving NLP through Marginalization of Hidden Syntactic Structure","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-viterbi-a-algorithm-for-k-best","title":"Iterative Viterbi A* Algorithm for K-Best Sequential Decoding","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-inference-of-named-entity-recognition","title":"Joint Inference of Named Entity Recognition and Normalization for Tweets","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-independent-named-entity","title":"Language Independent Named Entity Identification using Wikipedia","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-find-translations-and","title":"Learning to Find Translations and Transliterations on the Web","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-mcmc-efficient-inference-by","title":"Monte Carlo MCMC: Efficient Inference by Approximate Sampling","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-named-entity-recognition-using","title":"Multilingual Named Entity Recognition using Parallel Data and Metadata from Wikipedia","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"no-noun-phrase-left-behind-detecting-and","title":"No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quickview-nlp-based-tweet-search","title":"QuickView: NLP-based Tweet Search","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-named-entities-in-two-distinct","title":"Structured Named Entities in two distinct press corpora: Contemporary Broadcast News and Old Newspapers","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"subgroup-detector-a-system-for-detecting","title":"Subgroup Detector: A System for Detecting Subgroups in Online Discussions","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-a-multilingual-semantic","title":"Towards Building a Multilingual Semantic Network: Identifying Interlingual Links in Wikipedia","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-named-entity-rule-induction","title":"Towards Efficient Named-Entity Rule Induction for Customizability","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"umcc_dlsi-multidimensional-lexical-semantic","title":"UMCC\\_DLSI: Multidimensional Lexical-Semantic Textual Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-stepwise-approach-for-de-identifying","title":"A Hybrid Stepwise Approach for De-identifying Person Names in Clinical Documents","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-coreference-resolution","title":"Active Learning for Coreference Resolution","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-coreference-resolution-1","title":"Active Learning for Coreference Resolution","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptation-dun-systeme-de-reconnaissance","title":"Adaptation d'un syst\\`eme de reconnaissance d'entit\\'es nomm\\'ees pour le fran\\ccais \\`a l'anglais \\`a moindre co\\^ut (Adapting a French Named Entity Recognition System to English with Minimal Costs) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"apples-to-oranges-evaluating-image","title":"Apples to Oranges: Evaluating Image Annotations from Natural Language Processing Systems","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-animacy-classification","title":"Automatic Animacy Classification","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-approaches-for-gene-drug","title":"Automatic Approaches for Gene-Drug Interaction Extraction from Biomedical Text: Corpus and Comparative Evaluation","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-biomedical-ontologies-for","title":"Bootstrapping Biomedical Ontologies for Scientific Text using NELL","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-gene-sentences-in-biomedical","title":"Classifying Gene Sentences in Biomedical Literature by Combining High-Precision Gene Identifiers","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-the-right-supervisor-expert-finding","title":"Finding the Right Supervisor: Expert-Finding in a University Domain","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-comparable-corpora-using-lda","title":"Identifying Comparable Corpora Using LDA","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-mcmc-efficient-inference-by-1","title":"Monte Carlo MCMC: Efficient Inference by Sampling Factors","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nudging-the-envelope-of-direct-transfer","title":"Nudging the Envelope of Direct Transfer Methods for Multilingual Named Entity Recognition","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reperage-des-entites-nommees-pour-larabe","title":"Rep\\'erage des entit\\'es nomm\\'ees pour l'arabe : adaptation non-supervis\\'ee et combinaison de syst\\`emes (Named Entity Recognition for Arabic : Unsupervised adaptation and Systems combination) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-intelius-nickname-collection-quantitative","title":"The Intelius Nickname Collection: Quantitative Analyses from Billions of Public Records","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-data-and-analysis-resourcea-fora-ana","title":"A data and analysis resource for an experiment in text mining a collection of micro-blogs on a political topic.","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-disambiguation-resource-extracted-from","title":"A disambiguation resource extracted from Wikipedia for semantic annotation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-rough-set-formalization-of-quantitative","title":"A Rough Set Formalization of Quantitative Evaluation with Ambiguity","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aleda-a-free-large-scale-entity-database-for","title":"Aleda, a free large-scale entity database for French","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-framework-for-named-entity","title":"An Adaptive Framework for Named Entity Combination","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-lexical-semantic-classification-of","title":"Automatic lexical semantic classification of nouns","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bulgarian-x-language-parallel-corpus","title":"Bulgarian X-language Parallel Corpus","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"calbc-releasing-the-final-corpora","title":"CALBC: Releasing the Final Corpora","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"centroids-gold-standards-with-distributional","title":"Centroids: Gold standards with distributional variation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-in-the-knowledge-base-population","title":"Challenges in the Knowledge Base Population Slot Filling Task","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-and-curating-a-cross-language-person","title":"Creating and Curating a Cross-Language Person-Entity Linking Collection","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-impact-of-external-lexical","title":"Evaluating the Impact of External Lexical Resources into a CRF-based Multiword Segmenter and Part-of-Speech Tagger","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-impact-of-phrase-recognition","title":"Evaluating the Impact of Phrase Recognition on Concept Tagging","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-a-complex-information","title":"Evaluation of a Complex Information Extraction Application in Specific Domain","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-named-entities-annotation-on-ocred","title":"Extended Named Entities Annotation on OCRed Documents: From Corpus Constitution to Evaluation Campaign","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hunor-a-hungarianrussian-parallel-corpus","title":"HunOr: A Hungarian---Russian Parallel Corpus","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inforex-a-web-based-tool-for-text-corpus","title":"Inforex -- a web-based tool for text corpus management and semantic annotation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-refinement-and-quality-checking-of","title":"Iterative Refinement and Quality Checking of Annotation Guidelines --- How to Deal Effectively with Semantically Sloppy Named Entity Types, such as Pathological Phenomena","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kpwr-towards-a-free-corpus-of-polish","title":"KPWr: Towards a Free Corpus of Polish","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"latvian-and-lithuanian-named-entity","title":"Latvian and Lithuanian Named Entity Recognition with TildeNER","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-categories-and-their-instances-by","title":"Learning Categories and their Instances by Contextual Features","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-resources-for-entity-linking","title":"Linguistic Resources for Entity Linking Evaluation: from Monolingual to Cross-lingual","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rembrandt-a-named-entity-recognition","title":"Rembrandt - a named-entity recognition framework","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rule-based-entity-recognition-and-coverage-of","title":"Rule-based Entity Recognition and Coverage of SNOMED CT in Swedish Clinical Text","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-section-segmentation-in-free-text","title":"Statistical Section Segmentation in Free-Text Clinical Records","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-structured-named-entity-recognition-on","title":"Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-named-entity-recognition-and-entity","title":"A Joint Named Entity Recognition and Entity Linking System","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-visual-analytics-methods-for","title":"Advanced Visual Analytics Methods for Literature Analysis","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"brat-a-web-based-tool-for-nlp-assisted-text","title":"brat: a Web-based Tool for NLP-Assisted Text Annotation","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coupling-knowledge-based-and-data-driven","title":"Coupling Knowledge-Based and Data-Driven Systems for Named Entity Recognition","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nerd-a-framework-for-unifying-named-entity","title":"NERD: A Framework for Unifying Named Entity Recognition and Disambiguation Extraction Tools","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recall-oriented-learning-of-named-entities-in","title":"Recall-Oriented Learning of Named Entities in Arabic Wikipedia","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-emotional-stability-in-twitter","title":"The Role of Emotional Stability in Twitter Conversations","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-classification-of-blog-posts-using","title":"Topic Classification of Blog Posts Using Distant Supervision","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-representations-in-probabilistic-models","title":"Tree Representations in Probabilistic Models for Extended Named Entities Detection","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"whats-in-a-name-entity-type-variation-across","title":"What's in a Name? Entity Type Variation across Two Biomedical Subdomains","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-learning-of-word-embeddings-via","title":"Multi-View Learning of Word Embeddings via CCA","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"biomedical-named-entity-recognition-using-1","title":"Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets","date":"2004-08-28","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"70c47a56b2539494c3cb1aa38084bcb2d38e5a7711c6308a626f0b22729ca338","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}