{"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/chunking/papers/5","list_of":"/task/chunking","task":"Chunking","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":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,447],"of":447,"counts":{"archive_papers_tagged":447,"with_a_code_link":120,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":447,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/chunking","prev":"/task/chunking/papers/4","next":null,"papers":[{"url":null,"slug":"crowd-prefers-the-middle-path-a-new-iaa","title":"Crowd Prefers the Middle Path: A New IAA Metric for Crowdsourcing Reveals Turker Biases in Query Segmentation","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entailment-an-effective-metric-for-comparing","title":"Entailment: An Effective Metric for Comparing and Evaluating Hierarchical and Non-hierarchical Annotation Schemes","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"guitar-based-pronominal-anaphora-resolution","title":"GuiTAR-based Pronominal Anaphora Resolution in Bengali","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hidden-markov-tree-models-for-semantic-class","title":"Hidden Markov tree models for semantic class induction","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-annotators-behaviour-using","title":"Investigation of annotator's behaviour using eye-tracking data","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-lemmatise-polish-noun-phrases","title":"Learning to lemmatise Polish noun phrases","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-transduction-grammar-induction","title":"Unsupervised Transduction Grammar Induction via Minimum Description Length","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uzh-in-bionlp-2013","title":"UZH in BioNLP 2013","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-morphological-enrichment-of-a","title":"Automatic Morphological Enrichment of a Morphologically Underspecified Treebank","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/cleartk-timeml-a-minimalist-approach-to","slug":"cleartk-timeml-a-minimalist-approach-to","title":"ClearTK-TimeML: A minimalist approach to TempEval 2013","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-top-down-and-bottom-up-search-for","title":"Combining Top-down and Bottom-up Search for Unsupervised Induction of Transduction Grammars","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"compound-embedding-features-for-semi","title":"Compound Embedding Features for Semi-supervised Learning","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-strategies-for-streaming-speech","title":"Segmentation Strategies for Streaming Speech Translation","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"symbolic-and-statistical-learning-for","title":"Symbolic and statistical learning for chunking : comparison and combinations (Apprentissage symbolique et statistique pour le chunking:comparaison et combinaisons) [in French]","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-constraint-grammar-for-chunking","title":"Using Constraint Grammar for Chunking","date":"2013-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"obituary-george-a-miller","title":"Obituary: George A. Miller","date":"2013-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-conditional-random-field-based-traditional","title":"A Conditional Random Field-based Traditional Chinese Base Phrase Parser for SIGHAN Bake-off 2012 Evaluation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-for-discourse-argument","title":"A Unified Framework for Discourse Argument Identification via Shallow Semantic Parsing","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-finite-state-to-inversion-transductions","title":"From Finite-State to Inversion Transductions: Toward Unsupervised Bilingual Grammar Induction","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"noun-group-and-verb-group-identification-for","title":"Noun Group and Verb Group Identification for Hindi","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-representation-learning-for","title":"Semi-supervised Representation Learning for Domain Adaptation using Dynamic Dependency Networks","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-parsing-with-double-sequential","title":"Sentence Parsing with Double Sequential Labeling in Traditional Chinese Parsing Task","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-of-vietnamese-person-named-entity","title":"A Model of Vietnamese Person Named Entity Question Answering System","date":"2012-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cost-sensitive-part-of-speech-tagging","title":"A Cost Sensitive Part-of-Speech Tagging: Differentiating Serious Errors from Minor Errors","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reranking-model-for-discourse-segmentation","title":"A Reranking Model for Discourse Segmentation using Subtree Features","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":"exploiting-chunk-level-features-to-improve","title":"Exploiting Chunk-level Features to Improve Phrase Chunking","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-robust-part-of-speech-tagging-using","title":"Fast and Robust Part-of-Speech Tagging Using Dynamic Model Selection","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-statistical-machine-translation-5","title":"Improving Statistical Machine Translation through co-joining parts of verbal constructs in English-Hindi translation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-error-detection-at-two-levels-of","title":"Simultaneous error detection at two levels of syntactic annotation","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":"apprentissage-automatique-dun-chunker-pour-le","title":"Apprentissage automatique d'un chunker pour le fran\\ccais (Machine Learning of a chunker for French) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-unsupervised-feature-learning-for","title":"Deep Unsupervised Feature Learning for Natural Language Processing","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enrichir-et-raisonner-sur-des-espaces","title":"Enrichir et raisonner sur des espaces s\\'emantiques pour l'attribution de mots-cl\\'es (Enriching and reasoning on semantic spaces for keyword extraction) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"la-structuration-prosodique-et-les-relations","title":"La structuration prosodique et les relations syntaxe/ prosodie dans le discours politique (Prosodic Structuring and the Syntax-Prosody Relationship in Political Speech) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"un-segmenteur-etiqueteur-et-un-chunker-pour","title":"Un segmenteur-\\'etiqueteur et un chunker pour le fran\\ccais (A Segmenter-POS Labeller and a Chunker for French) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-concise-query-language-with-search-and","title":"A Concise Query Language with Search and Transform Operations for Corpora with Multiple Levels of Annotation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-japanese-compound-functional","title":"Detecting Japanese Compound Functional Expressions using Canonical/Derivational Relation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-recall-of-a-discourse-parser-by","title":"Improving the Recall of a Discourse Parser by Constraint-based Postprocessing","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"open-source-boundary-annotated-corpus-for","title":"Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-phrase-breaks-in-classical-and","title":"Predicting Phrase Breaks in Classical and Modern Standard Arabic Text","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rombac-the-romanian-balanced-annotated-corpus","title":"ROMBAC: The Romanian Balanced Annotated Corpus","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"yadac-yet-another-dialectal-arabic-corpus","title":"YADAC: Yet another Dialectal Arabic Corpus","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistically-adapted-structural-query","title":"Linguistically-Adapted Structural Query Annotation for Digital Libraries in the Social Sciences","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phacts-about-activation-based-word-similarity","title":"PHACTS about activation-based word similarity effects","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":"forgetting-exceptions-is-harmful-in-language","title":"Forgetting Exceptions is Harmful in Language Learning","date":"1998-12-22","arxiv_id":"cs/9812021","repositories_listed":0,"syntology":null}],"record_sha256":"a256cd8f34ee3b1238b22d298fd69354e57d356f0264b9e1d3d2b6384cd1083c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}