{"id":"https://openalex.org/W1984186257","doi":"https://doi.org/10.1145/1645953.1646218","title":"Combining labeled and unlabeled data with word-class distribution learning","display_name":"Combining labeled and unlabeled data with word-class distribution learning","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W1984186257","doi":"https://doi.org/10.1145/1645953.1646218","mag":"1984186257"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","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/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanjun Qi","raw_affiliation_strings":["NEC Labs America Inc, Princeton, NJ, USA","[NEC Laboratories America, Inc, Princeton, NJ, USA]"],"affiliations":[{"raw_affiliation_string":"NEC Labs America Inc, Princeton, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"[NEC Laboratories America, Inc, Princeton, NJ, USA]","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["NEC Labs America Inc, Princeton, NJ, USA","[NEC Laboratories America, Inc, Princeton, NJ, USA]"],"affiliations":[{"raw_affiliation_string":"NEC Labs America Inc, Princeton, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"[NEC Laboratories America, Inc, Princeton, NJ, USA]","institution_ids":["https://openalex.org/I20089843"]}]},{"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":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]},{"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":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"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/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Weston","raw_affiliation_strings":["NEC Labs America Inc, Princeton, NJ, USA","[NEC Laboratories America, Inc, Princeton, NJ, USA]"],"affiliations":[{"raw_affiliation_string":"NEC Labs America Inc, Princeton, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"[NEC Laboratories America, Inc, Princeton, NJ, USA]","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101887931"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.9033,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.79741552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1737","last_page":"1740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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":0.9948999881744385,"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":0.7851285934448242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7182824611663818},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.629014253616333},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6257483959197998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6056001782417297},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.6049678921699524},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5728858709335327},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5666890740394592},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5106378197669983},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48821762204170227},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4458153247833252},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4386236369609833},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4180997908115387},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.41352757811546326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4022712707519531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3854295611381531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35465043783187866},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21726194024085999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12151297926902771},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08403295278549194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851285934448242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7182824611663818},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.629014253616333},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6257483959197998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6056001782417297},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.6049678921699524},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5728858709335327},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5666890740394592},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5106378197669983},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48821762204170227},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4458153247833252},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4386236369609833},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4180997908115387},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.41352757811546326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4022712707519531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3854295611381531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35465043783187866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21726194024085999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12151297926902771},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08403295278549194},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1645953.1646218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.3079","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.3079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~qyj/papersA08/wcdl-cikm09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W155855048","https://openalex.org/W1638608766","https://openalex.org/W1815876077","https://openalex.org/W1994913251","https://openalex.org/W2020278455","https://openalex.org/W2020818097","https://openalex.org/W2048679005","https://openalex.org/W2056451646","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/W2139823104","https://openalex.org/W2144578941","https://openalex.org/W2145494108","https://openalex.org/W2149141985","https://openalex.org/W2163568299","https://openalex.org/W2273815277","https://openalex.org/W2595697910","https://openalex.org/W2785349534","https://openalex.org/W2792932412","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2538661024"],"abstract_inverted_index":{"We":[0,98],"describe":[1],"a":[2,57,124],"novel":[3],"simple":[4],"and":[5,15,55,91,104],"highly":[6],"scalable":[7],"semi-supervised":[8],"method":[9,101],"called":[10],"Word-Class":[11],"Distribution":[12],"Learning":[13],"(WCDL),":[14],"apply":[16],"it":[17],"task":[18],"of":[19],"information":[20],"extraction":[21],"(IE)":[22],"by":[23,44],"utilizing":[24],"unlabeled":[25,53],"sentences":[26],"to":[27,83,96],"improve":[28],"supervised":[29],"classification":[30],"methods.":[31],"WCDL":[32,87,111],"iteratively":[33],"builds":[34],"class":[35],"label":[36],"distributions":[37,62],"for":[38],"each":[39],"word":[40,64],"in":[41,51,121],"the":[42,52,131],"dictionary":[43],"averaging":[45],"predicted":[46],"labels":[47],"over":[48,114],"all":[49],"cases":[50],"corpus,":[54],"re-training":[56],"base":[58],"classifier":[59],"adding":[60],"these":[61],"as":[63],"features.":[65],"In":[66],"contrast,":[67],"traditional":[68],"self-training":[69],"or":[70,118],"co-training":[71],"methods":[72],"self-labeled":[73],"examples":[74],"(rather":[75],"than":[76],"features)":[77],"which":[78],"can":[79],"degrade":[80],"performance":[81],"due":[82],"incestuous":[84],"learning":[85],"bias.":[86],"exhibits":[88],"robust":[89],"behavior,":[90],"has":[92],"no":[93],"difficult":[94],"parameters":[95],"tune.":[97],"applied":[99],"our":[100],"on":[102,130],"German":[103,132],"English":[105],"name":[106],"entity":[107],"recognition":[108],"(NER)":[109],"tasks.":[110],"shows":[112],"improvements":[113],"self-training,":[115],"multi-task":[116],"semi-supervision":[117],"supervision":[119],"alone,":[120],"particular":[122],"yielding":[123],"state-of-the":[125],"art":[126],"75.72":[127],"F1":[128],"score":[129],"NER":[133],"task.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}