{"id":"https://openalex.org/W2860246576","doi":"https://doi.org/10.18653/v1/w18-6113","title":"Orthogonal Matching Pursuit for Text Classification","display_name":"Orthogonal Matching Pursuit for Text Classification","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2860246576","doi":"https://doi.org/10.18653/v1/w18-6113","mag":"2860246576"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6113","pdf_url":"https://www.aclweb.org/anthology/W18-6113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065352009","display_name":"Konstantinos Skianis","orcid":"https://orcid.org/0009-0002-8804-6320"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Konstantinos Skianis","raw_affiliation_strings":["LIX, cole Polytechnique, France","\u00c9cole Polytechnique, Palaiseau, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIX, cole Polytechnique, France","institution_ids":["https://openalex.org/I4210139461"]},{"raw_affiliation_string":"\u00c9cole Polytechnique, Palaiseau, France","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079375197","display_name":"Nikolaos Tziortziotis","orcid":"https://orcid.org/0000-0002-2175-2610"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nikolaos Tziortziotis","raw_affiliation_strings":["LIX, cole Polytechnique, France","\u00c9cole Polytechnique, Palaiseau, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIX, cole Polytechnique, France","institution_ids":["https://openalex.org/I4210139461"]},{"raw_affiliation_string":"\u00c9cole Polytechnique, Palaiseau, France","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057695979","display_name":"Michalis Vazirgiannis","orcid":"https://orcid.org/0000-0001-5923-4440"},"institutions":[{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["FR","GR"],"is_corresponding":false,"raw_author_name":"Michalis Vazirgiannis","raw_affiliation_strings":["Athens University of Economics and Business, Greece","LIX, cole Polytechnique, France","Athens University of Economics and Business, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707"]},{"raw_affiliation_string":"LIX, cole Polytechnique, France","institution_ids":["https://openalex.org/I4210139461"]},{"raw_affiliation_string":"Athens University of Economics and Business, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0758432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8745619058609009},{"id":"https://openalex.org/keywords/matching-pursuit","display_name":"Matching pursuit","score":0.869958758354187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6438796520233154},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5931297540664673},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5592223405838013},{"id":"https://openalex.org/keywords/lasso","display_name":"Lasso (programming language)","score":0.5416333079338074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5187268853187561},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5173563361167908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5136929750442505},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5104836225509644},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.481172651052475},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4665009379386902},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39547887444496155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20791494846343994},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0936654806137085},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.0759439766407013}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8745619058609009},{"id":"https://openalex.org/C156872377","wikidata":"https://www.wikidata.org/wiki/Q6786281","display_name":"Matching pursuit","level":3,"score":0.869958758354187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438796520233154},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5931297540664673},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5592223405838013},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.5416333079338074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5187268853187561},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5173563361167908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5136929750442505},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5104836225509644},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.481172651052475},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4665009379386902},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39547887444496155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20791494846343994},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0936654806137085},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.0759439766407013},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w18-6113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6113","pdf_url":"https://www.aclweb.org/anthology/W18-6113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.04715","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.04715","pdf_url":"https://arxiv.org/pdf/1807.04715","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2860246576","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1807.04715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1807.04715","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.04715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6113","pdf_url":"https://www.aclweb.org/anthology/W18-6113.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2860246576.pdf","grobid_xml":"https://content.openalex.org/works/W2860246576.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1504194272","https://openalex.org/W1516568895","https://openalex.org/W1962147060","https://openalex.org/W1967807490","https://openalex.org/W1984915212","https://openalex.org/W2047028564","https://openalex.org/W2078204800","https://openalex.org/W2095705004","https://openalex.org/W2103385190","https://openalex.org/W2106398669","https://openalex.org/W2114524997","https://openalex.org/W2116148865","https://openalex.org/W2122825543","https://openalex.org/W2126976013","https://openalex.org/W2127271355","https://openalex.org/W2137565990","https://openalex.org/W2147152072","https://openalex.org/W2150593711","https://openalex.org/W2153579005","https://openalex.org/W2155195660","https://openalex.org/W2158536343","https://openalex.org/W2163302275","https://openalex.org/W2163306339","https://openalex.org/W2164278908","https://openalex.org/W2290902083","https://openalex.org/W2565214228","https://openalex.org/W2569656908","https://openalex.org/W2740515581","https://openalex.org/W2953141406"],"related_works":["https://openalex.org/W2963863713","https://openalex.org/W2951620296","https://openalex.org/W2513160779","https://openalex.org/W81789593","https://openalex.org/W2088863496","https://openalex.org/W46904730","https://openalex.org/W2903030747","https://openalex.org/W3004799001","https://openalex.org/W1501346273","https://openalex.org/W1543005411","https://openalex.org/W2565911910","https://openalex.org/W2573272389","https://openalex.org/W2932958742","https://openalex.org/W2729562159","https://openalex.org/W2902250178","https://openalex.org/W2910392026","https://openalex.org/W2908353841","https://openalex.org/W2797637862","https://openalex.org/W3099014258","https://openalex.org/W2159402886"],"abstract_inverted_index":{"In":[0,43],"text":[1,59],"classification,":[2],"the":[3,10,29,38,58],"problem":[4],"of":[5,40,77],"overfitting":[6],"arises":[7],"due":[8],"to":[9,23,73,92],"high":[11],"dimensionality,":[12],"making":[13],"regularization":[14],"essential.":[15],"Although":[16],"classic":[17],"regularizers":[18,33],"provide":[19,34],"sparsity,":[20],"they":[21],"fail":[22],"return":[24],"highly":[25],"accurate":[26],"models.":[27,98],"On":[28],"contrary,":[30],"state-of-the-art":[31],"group-lasso":[32],"better":[35],"results":[36],"at":[37],"expense":[39],"low":[41],"sparsity.":[42],"this":[44],"paper,":[45],"we":[46],"apply":[47],"a":[48],"greedy":[49],"variable":[50],"selection":[51],"algorithm,":[52],"called":[53],"Orthogonal":[54],"Matching":[55],"Pursuit,":[56],"for":[57],"classification":[60],"task.":[61],"We":[62],"also":[63],"extend":[64],"standard":[65],"group":[66],"OMP":[67,72,84],"by":[68],"introducing":[69],"overlapping":[70,75,86],"Group":[71],"handle":[74],"groups":[76],"features.":[78],"Empirical":[79],"analysis":[80],"verifies":[81],"that":[82],"both":[83],"and":[85,95,100],"GOMP":[87],"constitute":[88],"powerful":[89],"regularizers,":[90],"able":[91],"produce":[93],"effective":[94],"very":[96],"sparse":[97],"Code":[99],"data":[101],"are":[102],"available":[103],"online":[104],"1":[105],".":[106]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}