{"id":"https://openalex.org/W2000718226","doi":"https://doi.org/10.3115/1621474.1621516","title":"JHU1","display_name":"JHU1","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2000718226","doi":"https://doi.org/10.3115/1621474.1621516","mag":"2000718226"},"language":"en","primary_location":{"id":"doi:10.3115/1621474.1621516","doi":"https://doi.org/10.3115/1621474.1621516","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621474.1621516","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621474.1621516","source":{"id":"https://openalex.org/S4363608670","display_name":"International Workshop on Semantic Evaluation (SemEval)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Semantic Evaluations - SemEval '07","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.5555/1621474.1621516","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113813635","display_name":"Delip Rao","orcid":"https://orcid.org/0000-0002-4534-9906","observed_orcids":["https://orcid.org/0000-0002-4534-9906"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Delip Rao","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080735926","display_name":"Nikesh Garera","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikesh Garera","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015876016","display_name":"David Yarowsky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Yarowsky","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.9707,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91081229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8804000020027161,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8804000020027161,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.07039999961853027,"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":0.026499999687075615,"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/person-name-disambiguation","display_name":"person name disambiguation","score":0.9850000143051147},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.8840000033378601},{"id":"https://openalex.org/keywords/document-vectors","display_name":"document vectors","score":0.6169999837875366},{"id":"https://openalex.org/keywords/polysemy","display_name":"polysemy","score":0.8830000162124634},{"id":"https://openalex.org/keywords/shared-task","display_name":"shared task","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221824169158936},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7084085941314697},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6122817993164062},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5507305264472961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48741844296455383},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.485777884721756},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4578494131565094},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4531063437461853},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44192394614219666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3940197229385376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3922179341316223},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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":1,"locations":[{"id":"doi:10.3115/1621474.1621516","doi":"https://doi.org/10.3115/1621474.1621516","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621474.1621516","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621474.1621516","source":{"id":"https://openalex.org/S4363608670","display_name":"International Workshop on Semantic Evaluation (SemEval)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Semantic Evaluations - SemEval '07","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1621474.1621516","doi":"https://doi.org/10.3115/1621474.1621516","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1621474.1621516","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1621474.1621516","source":{"id":"https://openalex.org/S4363608670","display_name":"International Workshop on Semantic Evaluation (SemEval)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Semantic Evaluations - SemEval '07","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2000718226.pdf","grobid_xml":"https://content.openalex.org/works/W2000718226.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1982678692","https://openalex.org/W2121080163","https://openalex.org/W2153911474","https://openalex.org/W2161682962","https://openalex.org/W2426886874"],"related_works":["https://openalex.org/W7096923974","https://openalex.org/W2042551910","https://openalex.org/W1500296856","https://openalex.org/W7097515855","https://openalex.org/W2086789006","https://openalex.org/W1519147712","https://openalex.org/W2403740450","https://openalex.org/W80802106","https://openalex.org/W2157524182","https://openalex.org/W7097420605"],"abstract_inverted_index":{"This":[0,29],"paper":[1,43],"presents":[2],"an":[3],"approach":[4],"to":[5,25],"person":[6],"name":[7],"disambiguation":[8],"using":[9],"K-means":[10],"clustering":[11],"on":[12,35,68],"rich-feature-enhanced":[13],"document":[14],"vectors,":[15],"augmented":[16],"with":[17],"additional":[18],"web-extracted":[19],"snippets":[20],"surrounding":[21],"the":[22,36,46,50,53,79],"polysemous":[23],"names":[24],"facilitate":[26],"term":[27],"bridging.":[28],"yields":[30],"a":[31],"significant":[32,47],"F-measure":[33],"improvement":[34],"shared":[37,60,80],"task":[38],"training":[39,54],"data":[40,57],"set.":[41],"The":[42],"also":[44],"illustrates":[45],"divergence":[48],"between":[49],"properties":[51],"of":[52],"and":[55],"test":[56],"in":[58,78],"this":[59],"task,":[61],"substantially":[62],"skewing":[63],"results.":[64],"Our":[65],"system":[66],"optimized":[67],"F0.2":[69],"rather":[70],"than":[71],"F0.5":[72],"would":[73],"have":[74],"achieved":[75],"top":[76],"performance":[77],"task.":[81]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
