{"id":"https://openalex.org/W1975163671","doi":"https://doi.org/10.1145/2505515.2505598","title":"Assessing sparse information extraction using semantic contexts","display_name":"Assessing sparse information extraction using semantic contexts","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W1975163671","doi":"https://doi.org/10.1145/2505515.2505598","mag":"1975163671"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & 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/A5100371517","display_name":"Peipei Li","orcid":"https://orcid.org/0000-0001-9142-448X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peipei Li","raw_affiliation_strings":["Hefei University of Technology, Hefei city, China","Hefei University of Technology, Hefei City, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei city, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Hefei University of Technology, Hefei City, China#TAB#","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063351917","display_name":"Haixun Wang","orcid":"https://orcid.org/0009-0007-0773-7004"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixun Wang","raw_affiliation_strings":["Microsoft Research Asia, Bei Jing, China","Microsoft Research Asia, Bei Jing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Bei Jing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Bei Jing, China#TAB#","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049400795","display_name":"Hongsong Li","orcid":"https://orcid.org/0000-0002-5681-3073"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Li","raw_affiliation_strings":["Microsoft Research Asia, Bei Jing, China","Microsoft Research Asia, Bei Jing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Bei Jing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Bei Jing, China#TAB#","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080738591","display_name":"Xindong Wu","orcid":"https://orcid.org/0000-0003-2396-1704"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xindong Wu","raw_affiliation_strings":["University of Vermont, Vermont, USA"],"affiliations":[{"raw_affiliation_string":"University of Vermont, Vermont, USA","institution_ids":["https://openalex.org/I111236770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100371517"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74343185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1709","last_page":"1714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/T11719","display_name":"Data Quality and Management","score":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8397433757781982},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7292227745056152},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7035538554191589},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.608870267868042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328949689865112},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5285030007362366},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5221472382545471},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.48778992891311646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43793079257011414},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43548884987831116},{"id":"https://openalex.org/keywords/semantic-compression","display_name":"Semantic compression","score":0.41295015811920166},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.36711740493774414},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.27060988545417786},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.20544487237930298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397433757781982},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7292227745056152},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7035538554191589},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.608870267868042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328949689865112},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5285030007362366},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5221472382545471},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.48778992891311646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43793079257011414},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43548884987831116},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.41295015811920166},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.36711740493774414},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.27060988545417786},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.20544487237930298},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2505515.2505598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W89857650","https://openalex.org/W157725869","https://openalex.org/W1512387364","https://openalex.org/W1576601469","https://openalex.org/W1980925709","https://openalex.org/W2017231698","https://openalex.org/W2024791376","https://openalex.org/W2043698120","https://openalex.org/W2063643557","https://openalex.org/W2068737686","https://openalex.org/W2103931177","https://openalex.org/W2119332773","https://openalex.org/W2129629757","https://openalex.org/W2132679783","https://openalex.org/W2138605095","https://openalex.org/W2144406616","https://openalex.org/W2145453687","https://openalex.org/W2154516098","https://openalex.org/W2161494021","https://openalex.org/W2169593823","https://openalex.org/W2622194446","https://openalex.org/W6753056052"],"related_works":["https://openalex.org/W2352298027","https://openalex.org/W4319940250","https://openalex.org/W842810586","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W2026635458","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W56350200","https://openalex.org/W2769783919"],"abstract_inverted_index":{"One":[0],"important":[1],"assumption":[2],"of":[3,40,57,100,102,112,123],"information":[4,19,91],"extraction":[5,20,124],"is":[6,21,66],"that":[7,117],"extractions":[8,33],"occurring":[9],"more":[10,13,136],"frequently":[11],"are":[12,32,76],"likely":[14],"to":[15,53,107],"be":[16],"correct.":[17],"Sparse":[18],"challenging":[22],"because":[23],"no":[24],"matter":[25],"how":[26],"big":[27],"a":[28,37,58,84,95],"corpus":[29],"is,":[30],"there":[31],"supported":[34],"by":[35,125],"only":[36],"small":[38],"amount":[39],"evidence":[41],"in":[42],"the":[43,55,63,70,74,110,121],"corpus.":[44],"A":[45],"pioneering":[46],"work":[47],"known":[48],"as":[49],"REALM":[50],"learns":[51],"HMMs":[52],"model":[54,109],"context":[56,75,111],"semantic":[59,87,97,113],"relationship":[60],"for":[61,73,89],"assessing":[62],"extractions.":[64],"This":[65],"quite":[67],"costly":[68],"and":[69,105],"semantics":[71],"revealed":[72],"not":[77],"explicit.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"introduce":[83],"lightweight,":[85],"explicit":[86],"approach":[88,119],"sparse":[90],"extraction.":[92],"We":[93],"use":[94],"large":[96],"network":[98],"consisting":[99],"millions":[101],"concepts,":[103],"entities,":[104],"attributes":[106],"explicitly":[108],"relationships.":[114],"Experiments":[115],"show":[116],"our":[118],"improves":[120],"F-score":[122],"at":[126],"least":[127],"11.2%":[128],"over":[129],"state-of-the-art,":[130],"HMM":[131],"based":[132],"approaches":[133],"while":[134],"maintaining":[135],"efficiency.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}