{"id":"https://openalex.org/W2126727667","doi":"https://doi.org/10.1109/icdm.2009.40","title":"Semi-Supervised Sequence Labeling with Self-Learned Features","display_name":"Semi-Supervised Sequence Labeling with Self-Learned Features","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2126727667","doi":"https://doi.org/10.1109/icdm.2009.40","mag":"2126727667"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2009.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2009.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Ninth IEEE International Conference on Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101887931","display_name":"Yanjun Qi","orcid":"https://orcid.org/0000-0002-5796-7453"},"institutions":[{"id":"https://openalex.org/I82700718","display_name":"Lear (United States)","ror":"https://ror.org/05bntm267","country_code":"US","type":"company","lineage":["https://openalex.org/I82700718"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanjun Qi","raw_affiliation_strings":["Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I82700718"]},{"raw_affiliation_string":"Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028780139","display_name":"Pavel P. Kuksa","orcid":"https://orcid.org/0000-0003-2248-6403"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel Kuksa","raw_affiliation_strings":["Department of Computer Science, Rutgers University, Piscataway, NJ, USA","Department of Computer Science Rutgers University  Piscataway NJ USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Computer Science Rutgers University  Piscataway NJ USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I82700718","display_name":"Lear (United States)","ror":"https://ror.org/05bntm267","country_code":"US","type":"company","lineage":["https://openalex.org/I82700718"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I82700718"]},{"raw_affiliation_string":"Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076226945","display_name":"Kunihiko Sadamasa","orcid":null},"institutions":[{"id":"https://openalex.org/I82700718","display_name":"Lear (United States)","ror":"https://ror.org/05bntm267","country_code":"US","type":"company","lineage":["https://openalex.org/I82700718"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunihiko Sadamasa","raw_affiliation_strings":["Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Machine Learing Department, NEC Laboratories of America, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I82700718"]},{"raw_affiliation_string":"Machine Learning Dept., NEC Labs. America, Inc., Princeton, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090341705","display_name":"Koray Kavukcuoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koray Kavukcuoglu","raw_affiliation_strings":["Computer Science Department, New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076635608","display_name":"Jason Weston","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Weston","raw_affiliation_strings":["Google Research NY, New York, NY, USA","Google Research NY, New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Research NY, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research NY, New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101887931"],"corresponding_institution_ids":["https://openalex.org/I82700718"],"apc_list":null,"apc_paid":null,"fwci":3.613,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93275467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"428","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","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/computer-science","display_name":"Computer science","score":0.812568187713623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.720061182975769},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6822998523712158},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6759144067764282},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6265533566474915},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.618381917476654},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5371561646461487},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5010092258453369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.450700044631958},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.429737389087677},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.429558128118515},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4207962155342102},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38796135783195496},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15904757380485535},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.11084184050559998},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0907084047794342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812568187713623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.720061182975769},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6822998523712158},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6759144067764282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6265533566474915},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.618381917476654},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5371561646461487},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5010092258453369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.450700044631958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.429737389087677},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.429558128118515},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4207962155342102},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38796135783195496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15904757380485535},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.11084184050559998},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0907084047794342},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2009.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2009.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Ninth IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.8238","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.8238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ronan.collobert.com/pub/matos/2009_slf_icdm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W155855048","https://openalex.org/W1479807131","https://openalex.org/W1574901103","https://openalex.org/W1579429723","https://openalex.org/W1634005169","https://openalex.org/W1638608766","https://openalex.org/W1815876077","https://openalex.org/W1984186257","https://openalex.org/W1994913251","https://openalex.org/W1996430422","https://openalex.org/W2019680624","https://openalex.org/W2020278455","https://openalex.org/W2020818097","https://openalex.org/W2048679005","https://openalex.org/W2052620491","https://openalex.org/W2056451646","https://openalex.org/W2061526129","https://openalex.org/W2078058974","https://openalex.org/W2097089247","https://openalex.org/W2107008379","https://openalex.org/W2111316763","https://openalex.org/W2116632765","https://openalex.org/W2117130368","https://openalex.org/W2125327503","https://openalex.org/W2130903752","https://openalex.org/W2134134392","https://openalex.org/W2139823104","https://openalex.org/W2142114717","https://openalex.org/W2144578941","https://openalex.org/W2145494108","https://openalex.org/W2147880316","https://openalex.org/W2149141985","https://openalex.org/W2150969560","https://openalex.org/W2154142897","https://openalex.org/W2273815277","https://openalex.org/W2293363371","https://openalex.org/W2785349534","https://openalex.org/W2952087486","https://openalex.org/W4285719527","https://openalex.org/W6634738089","https://openalex.org/W6636787954","https://openalex.org/W6676132248","https://openalex.org/W6679734692","https://openalex.org/W6680156883","https://openalex.org/W6680434193","https://openalex.org/W6681325634","https://openalex.org/W6681588610","https://openalex.org/W6682082992","https://openalex.org/W6747435310"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W2962906565","https://openalex.org/W3015678144","https://openalex.org/W1838576100","https://openalex.org/W2798423868","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2385598138"],"abstract_inverted_index":{"Typical":[0],"information":[1],"extraction":[2],"(IE)":[3],"systems":[4],"can":[5,58],"be":[6,59,126],"seen":[7],"as":[8,114,137],"tasks":[9],"assigning":[10],"labels":[11,81],"to":[12,38,67,128,152],"words":[13],"in":[14,44,71,85,102],"a":[15,35,47,72,123],"natural":[16],"language":[17],"sequence.":[18],"The":[19],"performance":[20],"is":[21,150],"restricted":[22],"by":[23],"the":[24,40,86,103,107,184,195],"availability":[25],"of":[26,49,75],"labeled":[27],"words.":[28],"To":[29],"tackle":[30],"this":[31,156,200],"issue,":[32],"we":[33],"propose":[34],"semi-supervised":[36],"approach":[37,157,201],"improve":[39],"sequence":[41],"labeling":[42],"procedure":[43],"IE":[45,161],"through":[46],"class":[48,92,130,140],"algorithms":[50],"with":[51,61,194],"self-learned":[52],"features":[53],"(SLF).":[54],"A":[55],"supervised":[56,185],"classifier":[57],"trained":[60],"annotated":[62],"text":[63],"sequences":[64],"and":[65,105,146,149,167,172],"used":[66],"classify":[68],"each":[69,97],"word":[70,98,100,116,124],"large":[73],"set":[74],"unannotated":[76],"sentences.":[77],"By":[78],"averaging":[79],"predicted":[80],"over":[82,183],"all":[83,188],"cases":[84],"unlabeled":[87],"corpus,":[88],"SLF":[89,119,143],"training":[90],"builds":[91],"label":[93],"distribution":[94],"patterns":[95],"for":[96],"(or":[99],"attribute)":[101],"dictionary":[104],"re-trains":[106],"current":[108],"model":[109],"iteratively":[110],"adding":[111],"these":[112],"distributions":[113],"extra":[115],"features.":[117],"Basic":[118],"models":[120],"how":[121],"likely":[122],"could":[125],"assigned":[127],"target":[129],"types.":[131],"Several":[132],"extensions":[133],"are":[134],"proposed,":[135],"such":[136],"learning":[138],"words'":[139],"boundary":[141],"distributions.":[142],"exhibits":[144],"robust":[145],"scalable":[147],"behaviour":[148],"easy":[151],"tune.":[153],"We":[154],"applied":[155],"on":[158,187],"four":[159],"classical":[160],"tasks:":[162],"named":[163],"entity":[164],"recognition":[165,176],"(German":[166],"English),":[168],"part-of-speech":[169],"tagging":[170],"(English)":[171],"one":[173],"gene":[174],"name":[175],"corpus.":[177],"Experimental":[178],"results":[179],"show":[180],"effective":[181],"improvements":[182],"baselines":[186],"tasks.":[189],"In":[190],"addition,":[191],"when":[192],"compared":[193],"closely":[196],"related":[197],"self-training":[198],"idea,":[199],"shows":[202],"favorable":[203],"advantages.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}