{"id":"https://openalex.org/W2152431819","doi":"https://doi.org/10.1145/2063576.2063781","title":"Facilitating pattern discovery for relation extraction with semantic-signature-based clustering","display_name":"Facilitating pattern discovery for relation extraction with semantic-signature-based clustering","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2152431819","doi":"https://doi.org/10.1145/2063576.2063781","mag":"2152431819"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102944075","display_name":"Yunyao Li","orcid":"https://orcid.org/0009-0002-0814-4634"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079463431","display_name":"Vivian S. Chu","orcid":"https://orcid.org/0000-0002-0304-3650"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivian Chu","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082904067","display_name":"Sebastian Blohm","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087053","display_name":"Microsoft (Germany)","ror":"https://ror.org/001dd4s60","country_code":"DE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210087053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Blohm","raw_affiliation_strings":["Microsoft Corporation, M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I4210087053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076801334","display_name":"Huaiyu Zhu","orcid":"https://orcid.org/0000-0001-6918-4088"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaiyu Zhu","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004469222","display_name":"Howard Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Ho","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8898,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87251475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1415","last_page":"1424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis Techniques","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/T11719","display_name":"Data Quality and Management","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8187209367752075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025257587432861},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6914709210395813},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.6217346787452698},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6175941824913025},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5502172708511353},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4970856010913849},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4221058487892151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4067579507827759},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3783646523952484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34394532442092896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12381049990653992}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8187209367752075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025257587432861},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6914709210395813},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.6217346787452698},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6175941824913025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5502172708511353},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4970856010913849},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4221058487892151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4067579507827759},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3783646523952484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34394532442092896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12381049990653992},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W70399244","https://openalex.org/W147952312","https://openalex.org/W168937915","https://openalex.org/W197270748","https://openalex.org/W1484413656","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1506285740","https://openalex.org/W1565862766","https://openalex.org/W1890589545","https://openalex.org/W1904009680","https://openalex.org/W1969483186","https://openalex.org/W1970381522","https://openalex.org/W1980925709","https://openalex.org/W1982912896","https://openalex.org/W2022760666","https://openalex.org/W2030408698","https://openalex.org/W2035266017","https://openalex.org/W2051317694","https://openalex.org/W2056354103","https://openalex.org/W2068737686","https://openalex.org/W2090125415","https://openalex.org/W2098720114","https://openalex.org/W2103931177","https://openalex.org/W2105286307","https://openalex.org/W2112646584","https://openalex.org/W2119057313","https://openalex.org/W2123143128","https://openalex.org/W2127218421","https://openalex.org/W2133990480","https://openalex.org/W2143349571","https://openalex.org/W2146191280","https://openalex.org/W2146960529","https://openalex.org/W2148540243","https://openalex.org/W2150588363","https://openalex.org/W2157302829","https://openalex.org/W2158407464","https://openalex.org/W2162590473","https://openalex.org/W2167435923","https://openalex.org/W2745750801","https://openalex.org/W2785321994","https://openalex.org/W4285719527","https://openalex.org/W6606032630","https://openalex.org/W6628750762","https://openalex.org/W6629638141","https://openalex.org/W6683883671"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W1990856605","https://openalex.org/W4387688064"],"abstract_inverted_index":{"Hand-crafted":[0],"textual":[1,31,68,147],"patterns":[2,32,148],"have":[3],"been":[4,17],"the":[5,22,27,46,55,62,121,157,162],"mainstay":[6],"device":[7],"of":[8,29,57,66,107,156],"practical":[9],"relation":[10,34,50,150],"extraction":[11,151],"for":[12,33,49,149],"decades.":[13],"However,":[14],"there":[15],"has":[16],"little":[18],"work":[19],"on":[20,78,87],"reducing":[21],"manual":[23,130,158],"effort":[24,159],"involved":[25],"in":[26],"discovery":[28,48],"effective":[30,146],"extraction.":[35,51],"In":[36],"this":[37],"paper,":[38],"we":[39,53],"propose":[40,72],"a":[41,67,73,133,154],"clustering-based":[42,139],"approach":[43,140],"to":[44,60,120],"facilitate":[45],"pattern":[47],"Specifically,":[52],"define":[54],"notion":[56],"semantic":[58,79],"signature":[59],"represent":[61],"most":[63],"salient":[64],"features":[65],"fragment.":[69],"We":[70],"then":[71],"novel":[74],"clustering":[75],"algorithm":[76],"based":[77],"signature,":[80],"S2C,":[81],"and":[82,100],"its":[83],"enhancement":[84],"S2C+.":[85],"Experiments":[86],"two":[88],"real-world":[89],"data":[90],"sets":[91],"show":[92],"that,":[93],"when":[94],"compared":[95],"with":[96,152],"k-means":[97,126],"clustering,":[98],"S2C":[99],"S2C+":[101],"are":[102,116],"at":[103,117],"least":[104,118],"an":[105],"order":[106],"magnitude":[108],"faster,":[109],"while":[110],"generating":[111],"high":[112],"quality":[113],"clusters":[114,123],"that":[115,137],"comparable":[119],"best":[122],"generated":[124],"by":[125,161],"without":[127],"requiring":[128],"any":[129],"tuning.":[131],"Finally,":[132],"user":[134],"study":[135],"confirms":[136],"our":[138],"can":[141],"indeed":[142],"help":[143],"users":[144],"discover":[145],"only":[153],"fraction":[155],"required":[160],"conventional":[163],"approach.":[164]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}