{"id":"https://openalex.org/W2091117392","doi":"https://doi.org/10.1162/coli_a_00202","title":"A Large-Scale Pseudoword-Based Evaluation Framework for State-of-the-Art Word Sense Disambiguation","display_name":"A Large-Scale Pseudoword-Based Evaluation Framework for State-of-the-Art Word Sense Disambiguation","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W2091117392","doi":"https://doi.org/10.1162/coli_a_00202","mag":"2091117392"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00202","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00202","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00202","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00202","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091017313","display_name":"Mohammad Taher Pilehvar","orcid":"https://orcid.org/0000-0003-3694-4006"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mohammad Taher Pilehvar","raw_affiliation_strings":["Sapienza University of Rome","Sapienza, university of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza, university of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":["Sapienza University of Rome","Sapienza, university of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza, university of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8415,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.98561002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"40","issue":"4","first_page":"837","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.9954000115394592,"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":0.8830925226211548},{"id":"https://openalex.org/keywords/pseudoword","display_name":"Pseudoword","score":0.8088228702545166},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8020375967025757},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6283717751502991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5862054824829102},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5373121500015259},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4664824306964874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45488643646240234},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.43409931659698486},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.4326803684234619},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42318564653396606},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37074410915374756},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.11355921626091003},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07352638244628906},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.07304579019546509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830925226211548},{"id":"https://openalex.org/C2780961231","wikidata":"https://www.wikidata.org/wiki/Q1369058","display_name":"Pseudoword","level":3,"score":0.8088228702545166},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8020375967025757},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6283717751502991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5862054824829102},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5373121500015259},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4664824306964874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45488643646240234},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.43409931659698486},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.4326803684234619},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42318564653396606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37074410915374756},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.11355921626091003},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07352638244628906},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.07304579019546509},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/coli_a_00202","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00202","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00202","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.639.5910","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.5910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wwwusers.di.uniroma1.it/~navigli/pubs/CL_2014_Pilehvar_Navigli.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.685.3036","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.3036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/J/J14/J14-4005.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:14987cf4a88c4afc86a5835c81977cac","is_oa":false,"landing_page_url":"https://doaj.org/article/14987cf4a88c4afc86a5835c81977cac","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 40, Iss 4 (2021)","raw_type":"article"},{"id":"pmh:oai:iris.uniroma1.it:11573/645254","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/645254","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00202","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00202","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00202","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2091117392.pdf","grobid_xml":"https://content.openalex.org/works/W2091117392.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W12553087","https://openalex.org/W31189740","https://openalex.org/W66953820","https://openalex.org/W78490001","https://openalex.org/W93439600","https://openalex.org/W99109353","https://openalex.org/W101497934","https://openalex.org/W125820043","https://openalex.org/W135437175","https://openalex.org/W158623153","https://openalex.org/W189991804","https://openalex.org/W193356382","https://openalex.org/W1486093399","https://openalex.org/W1487777768","https://openalex.org/W1519776800","https://openalex.org/W1525367170","https://openalex.org/W1555805532","https://openalex.org/W1557632449","https://openalex.org/W1576423642","https://openalex.org/W1580825123","https://openalex.org/W1606491415","https://openalex.org/W1647729745","https://openalex.org/W1738526829","https://openalex.org/W1803149581","https://openalex.org/W1851555520","https://openalex.org/W1889628180","https://openalex.org/W1921587136","https://openalex.org/W1970381522","https://openalex.org/W1972383226","https://openalex.org/W1976252502","https://openalex.org/W1977182536","https://openalex.org/W1977944732","https://openalex.org/W1981938229","https://openalex.org/W1983179002","https://openalex.org/W1999471173","https://openalex.org/W2003374509","https://openalex.org/W2031026221","https://openalex.org/W2033441998","https://openalex.org/W2047620598","https://openalex.org/W2054690340","https://openalex.org/W2055518963","https://openalex.org/W2065157922","https://openalex.org/W2075517337","https://openalex.org/W2077183781","https://openalex.org/W2079656678","https://openalex.org/W2081523373","https://openalex.org/W2085116970","https://openalex.org/W2093647425","https://openalex.org/W2096423148","https://openalex.org/W2101210369","https://openalex.org/W2101293500","https://openalex.org/W2101932620","https://openalex.org/W2102381086","https://openalex.org/W2102423300","https://openalex.org/W2106532854","https://openalex.org/W2106851243","https://openalex.org/W2109914305","https://openalex.org/W2110881686","https://openalex.org/W2118108643","https://openalex.org/W2120699290","https://openalex.org/W2121147707","https://openalex.org/W2122267153","https://openalex.org/W2127289991","https://openalex.org/W2129222572","https://openalex.org/W2131777816","https://openalex.org/W2135254172","https://openalex.org/W2141211166","https://openalex.org/W2144131929","https://openalex.org/W2147520877","https://openalex.org/W2149671658","https://openalex.org/W2149801387","https://openalex.org/W2150034910","https://openalex.org/W2157963512","https://openalex.org/W2159719802","https://openalex.org/W2159980159","https://openalex.org/W2166021673","https://openalex.org/W2170344111","https://openalex.org/W2170682101","https://openalex.org/W2171149802","https://openalex.org/W2186446900","https://openalex.org/W2192710297","https://openalex.org/W2250256197","https://openalex.org/W2250626537","https://openalex.org/W2250977517","https://openalex.org/W2251797829","https://openalex.org/W2252126225","https://openalex.org/W2436001372","https://openalex.org/W2528799029","https://openalex.org/W2786299737","https://openalex.org/W3105419723","https://openalex.org/W3149550307","https://openalex.org/W6601274740","https://openalex.org/W6629756878","https://openalex.org/W6634576042"],"related_works":["https://openalex.org/W2101293500","https://openalex.org/W2384058382","https://openalex.org/W4385570488","https://openalex.org/W2000205775","https://openalex.org/W2124313972","https://openalex.org/W2251529656","https://openalex.org/W2140343536","https://openalex.org/W2117805747","https://openalex.org/W2062413478","https://openalex.org/W2188275805"],"abstract_inverted_index":{"The":[0],"evaluation":[1,89],"of":[2,14,17,66,83,87,113,121,133,149,162,177],"several":[3],"tasks":[4],"in":[5,37],"lexical":[6],"semantics":[7],"is":[8,34],"often":[9],"limited":[10],"by":[11,81,97],"the":[12,67,91,110,129,147,160,167,178],"lack":[13],"large":[15,137],"amounts":[16],"manual":[18],"annotations,":[19],"not":[20,61],"only":[21],"for":[22,27,63,90,146],"training":[23],"purposes,":[24],"but":[25],"also":[26],"testing":[28],"purposes.":[29],"Word":[30],"Sense":[31],"Disambiguation":[32],"(WSD)":[33],"a":[35,56,71,84,142],"case":[36],"point,":[38],"as":[39],"hand-labeled":[40],"datasets":[41],"are":[42],"particularly":[43],"hard":[44],"and":[45,152,164,172],"time-consuming":[46],"to":[47,52,109,135],"create.":[48],"Consequently,":[49],"evaluations":[50],"tend":[51],"be":[53],"performed":[54],"on":[55,166],"small":[57],"scale,":[58],"which":[59,140,180],"does":[60],"allow":[62],"in-depth":[64,175],"analysis":[65,176],"factors":[68,179],"that":[69],"determine":[70],"systems'":[72],"performance.":[73,183],"In":[74],"this":[75,79,96,156],"paper":[76],"we":[77,103,127,158],"address":[78],"issue":[80],"means":[82],"realistic":[85],"simulation":[86],"large-scale":[88,143],"WSD":[92],"task.":[93],"We":[94],"do":[95],"providing":[98],"two":[99,106,168],"main":[100],"contributions:":[101],"First,":[102],"put":[104],"forward":[105],"novel":[107],"approaches":[108],"wide-coverage":[111],"generation":[112],"semantically":[114],"aware":[115],"pseudowords":[116],"(i.e.,":[117],"artificial":[118],"words":[119],"capable":[120],"modeling":[122],"real":[123],"polysemous":[124],"words);":[125],"second,":[126],"leverage":[128],"most":[130],"suitable":[131],"type":[132],"pseudoword":[134],"create":[136],"pseudosense-annotated":[138],"corpora,":[139],"enable":[141],"experimental":[144],"framework":[145],"comparison":[148],"state-of-the-art":[150],"supervised":[151],"knowledge-based":[153],"algorithms.":[154],"Using":[155],"framework,":[157],"study":[159],"impact":[161],"supervision":[163],"knowledge":[165],"major":[169],"disambiguation":[170],"paradigms":[171],"perform":[173],"an":[174],"affect":[181],"their":[182]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}