{"id":"https://openalex.org/W2166986236","doi":"https://doi.org/10.18653/v1/w13-5004","title":"Reconstructing Big Semantic Similarity Networks","display_name":"Reconstructing Big Semantic Similarity Networks","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2166986236","doi":"https://doi.org/10.18653/v1/w13-5004","mag":"2166986236"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w13-5004","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/w13-5004","pdf_url":"https://aclanthology.org/W13-5004.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 TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W13-5004.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085870473","display_name":"Ai He","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ai He","raw_affiliation_strings":["Information Sciences Institute#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034387013","display_name":"Shefali Sharma","orcid":"https://orcid.org/0000-0002-8821-6652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shefali Sharma","raw_affiliation_strings":["Information Sciences Institute#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040580626","display_name":"Chun\u2010Nan Hsu","orcid":"https://orcid.org/0000-0002-5240-4707"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Nan Hsu","raw_affiliation_strings":["University of California\u2014San Diego"],"affiliations":[{"raw_affiliation_string":"University of California\u2014San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085870473"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12405079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6892639398574829},{"id":"https://openalex.org/keywords/mahalanobis-distance","display_name":"Mahalanobis distance","score":0.6295322179794312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5437899231910706},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5410107970237732},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5205865502357483},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.5204420685768127},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5106905102729797},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48136645555496216},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4791140556335449},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4366661310195923},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42001986503601074},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3482004404067993},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3478022813796997},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16890743374824524},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11683374643325806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892639398574829},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.6295322179794312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437899231910706},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5410107970237732},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5205865502357483},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.5204420685768127},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5106905102729797},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48136645555496216},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4791140556335449},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4366661310195923},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42001986503601074},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3482004404067993},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3478022813796997},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16890743374824524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11683374643325806},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w13-5004","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/w13-5004","pdf_url":"https://aclanthology.org/W13-5004.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 TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.1775","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.1775","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/W/W13/W13-5004.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w13-5004","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/w13-5004","pdf_url":"https://aclanthology.org/W13-5004.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 TextGraphs-8 Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3497591915","display_name":null,"funder_award_id":"(NIH)","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2166986236.pdf","grobid_xml":"https://content.openalex.org/works/W2166986236.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W637283567","https://openalex.org/W1542928586","https://openalex.org/W1976618413","https://openalex.org/W2012231377","https://openalex.org/W2106053110","https://openalex.org/W2117154949","https://openalex.org/W2122090912","https://openalex.org/W2125993116","https://openalex.org/W2127008962","https://openalex.org/W2130556178","https://openalex.org/W2144935315","https://openalex.org/W2170682041","https://openalex.org/W2595142274","https://openalex.org/W2798909945","https://openalex.org/W2912522929","https://openalex.org/W2979473749","https://openalex.org/W3097609957"],"related_works":["https://openalex.org/W2515532094","https://openalex.org/W2790862734","https://openalex.org/W345943785","https://openalex.org/W2141406155","https://openalex.org/W3015962327","https://openalex.org/W2611813480","https://openalex.org/W2624745934","https://openalex.org/W2807562011","https://openalex.org/W3148922054","https://openalex.org/W2119226345"],"abstract_inverted_index":{"Distance":[0],"metric":[1,49],"learning":[2,44],"from":[3,50,117],"high":[4,23,57],"(thousands":[5],"or":[6,12],"more)":[7],"dimensional":[8,58],"data":[9,30,53,135],"with":[10],"hundreds":[11],"thousands":[13],"of":[14,45,84,114],"classes":[15],"is":[16,25,92],"intractable":[17],"but":[18],"in":[19,34,55,123,140],"NLP":[20],"and":[21,68,76,94,120,136],"IR,":[22],"dimensionality":[24,67],"usually":[26],"required":[27],"to":[28,41,79,108],"represent":[29],"points,":[31],"such":[32],"as":[33],"modeling":[35],"semantic":[36,112],"similarity.This":[37],"paper":[38],"presents":[39],"algorithms":[40],"scale":[42],"up":[43],"a":[46,51,56,69,81,100],"Mahalanobis":[47],"distance":[48],"large":[52,82],"graph":[54],"space.Our":[59],"novel":[60],"contributions":[61],"include":[62],"random":[63],"projection":[64],"that":[65,73,87,127],"reduces":[66],"new":[70,89],"objective":[71,90],"function":[72,91],"regularizes":[74],"intra-class":[75],"inter-class":[77],"distances":[78],"handle":[80,131],"number":[83],"classes.We":[85],"show":[86,126],"the":[88,118,132],"convex":[93],"can":[95,130],"be":[96],"efficiently":[97],"optimized":[98],"by":[99],"stochastic-batch":[101],"subgradient":[102],"descent":[103],"method.We":[104],"applied":[105],"our":[106,128],"algorithm":[107,129],"two":[109],"different":[110],"domains;":[111],"similarity":[113],"documents":[115],"collected":[116],"Web,":[119],"phenotype":[121],"descriptions":[122],"genomic":[124],"data.Experiments":[125],"high-dimensional":[133],"big":[134],"outperform":[137],"competing":[138],"approximations":[139],"both":[141],"domains.":[142]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}