{"id":"https://openalex.org/W2962716526","doi":"https://doi.org/10.1145/3148011.3148016","title":"SimDoc","display_name":"SimDoc","publication_year":2017,"publication_date":"2017-12-04","ids":{"openalex":"https://openalex.org/W2962716526","doi":"https://doi.org/10.1145/3148011.3148016","mag":"2962716526"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3148016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5044599885","display_name":"Gaurav Maheshwari","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gaurav Maheshwari","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025276555","display_name":"Priyansh Trivedi","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Priyansh Trivedi","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070120761","display_name":"Harshita Sahijwani","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harshita Sahijwani","raw_affiliation_strings":["Emory University, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011682613","display_name":"Kunal Jha","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kunal Jha","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017847295","display_name":"Sourish Dasgupta","orcid":"https://orcid.org/0000-0003-0507-6824"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sourish Dasgupta","raw_affiliation_strings":["Rygbee Inc., Denver, USA"],"affiliations":[{"raw_affiliation_string":"Rygbee Inc., Denver, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.187,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":6,"citation_normalized_percentile":{"value":0.639425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":82},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9762,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9747,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4922332}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3148016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":14,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1996476189","https://openalex.org/W2061263584","https://openalex.org/W2087064593","https://openalex.org/W2106490775","https://openalex.org/W2112050062","https://openalex.org/W2120779048","https://openalex.org/W2161002933","https://openalex.org/W2165612380","https://openalex.org/W2165979181","https://openalex.org/W2250539671","https://openalex.org/W2250825496","https://openalex.org/W2745750801","https://openalex.org/W2997185401"],"related_works":["https://openalex.org/W4391913857","https://openalex.org/W2748952813","https://openalex.org/W2530322880","https://openalex.org/W2478288626","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2350741829","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Document":[0],"similarity":[1,23,71,110],"is":[2,50,56],"the":[3,7],"problem":[4],"of":[5,14,86],"estimating":[6,59],"degree":[8],"to":[9,96,107,111],"which":[10,49],"a":[11,45,67,92,104],"given":[12],"pair":[13],"documents":[15,77],"has":[16],"similar":[17],"semantic":[18,69,99],"content.":[19],"An":[20],"accurate":[21],"document":[22,33,70,131,139],"measure":[24],"can":[25],"improve":[26],"several":[27],"enterprise":[28],"relevant":[29],"tasks":[30],"such":[31,137],"as":[32,78,138],"clustering,":[34],"text":[35],"mining,":[36],"and":[37,133],"question-answering.":[38],"In":[39,116],"this":[40,63],"paper,":[41],"we":[42,65,90,119],"show":[43,120],"that":[44,121],"document's":[46],"thematic":[47],"flow,":[48],"often":[51],"disregarded":[52],"by":[53],"bag-of-word":[54],"techniques,":[55],"pivotal":[57],"in":[58,128],"their":[60,98],"similarity.":[61,100],"To":[62],"end,":[64],"propose":[66],"novel":[68,105],"framework,":[72],"called":[73],"SimDoc.":[74],"We":[75,101],"model":[76],"topic-sequences,":[79],"where":[80],"topics":[81],"represent":[82],"latent":[83],"generative":[84],"clusters":[85],"related":[87],"words.":[88],"Then,":[89],"use":[91],"sequence":[93],"alignment":[94],"algorithm":[95],"estimate":[97],"further":[102],"conceptualize":[103],"mechanism":[106],"compute":[108],"topic-topic":[109],"fine":[112],"tune":[113],"our":[114,117],"system.":[115],"experiments,":[118],"SimDoc":[122],"outperforms":[123],"many":[124],"contemporary":[125],"bag-of-words":[126],"techniques":[127],"accurately":[129],"computing":[130],"similarity,":[132],"on":[134],"practical":[135],"applications":[136],"clustering.":[140]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2962716526","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2024-12-24T07:57:48.502282","created_date":"2019-07-30"}