{"id":"https://openalex.org/W2575166203","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-065","title":"Revisiting Known-Item Retrieval in Degraded Document Collections","display_name":"Revisiting Known-Item Retrieval in Degraded Document Collections","publication_year":2016,"publication_date":"2016-02-17","ids":{"openalex":"https://openalex.org/W2575166203","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-065","mag":"2575166203"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-065","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-065","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-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/A5015356898","display_name":"Jason Soo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Soo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062591304","display_name":"Ophir Frieder","orcid":"https://orcid.org/0000-0001-5076-8171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2993,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87816055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"28","issue":"17","first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9865000247955322,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9865000247955322,"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/T10028","display_name":"Topic Modeling","score":0.9829000234603882,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9314000010490417,"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":0.7512402534484863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6402212381362915},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.6258963942527771},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.594062864780426},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.582872748374939},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5372355580329895},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5048059225082397},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.45576179027557373},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.43630537390708923},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.4361620843410492},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4360157251358032},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4323924779891968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37299153208732605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30949658155441284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1030680239200592},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08783844113349915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512402534484863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6402212381362915},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.6258963942527771},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.594062864780426},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.582872748374939},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5372355580329895},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5048059225082397},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.45576179027557373},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.43630537390708923},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.4361620843410492},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4360157251358032},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4323924779891968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37299153208732605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30949658155441284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1030680239200592},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08783844113349915},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-065","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-065","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W2998448420","https://openalex.org/W1974038726","https://openalex.org/W1953626159","https://openalex.org/W1981012585","https://openalex.org/W2113640060","https://openalex.org/W4231510080","https://openalex.org/W146601322","https://openalex.org/W3195157097","https://openalex.org/W3045444188"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2],"software":[3],"converts":[4],"an":[5,120],"image":[6],"of":[7,34,43,71,122,131],"text":[8,11],"to":[9,22,27,51,112],"a":[10,41,82,102],"document":[12,25],"but":[13],"typically":[14],"degrades":[15],"the":[16,24,32,77,87,97,113],"document's":[17],"contents.":[18],"Correcting":[19],"such":[20],"degradation":[21],"enable":[23],"set":[26],"be":[28],"queried":[29],"effectively":[30],"is":[31],"focus":[33],"this":[35],"work.":[36],"The":[37,116],"described":[38,117],"approach":[39,118],"uses":[40],"fusion":[42],"substring":[44],"generation":[45],"rules":[46],"and":[47,73,90,108,124,134],"context":[48],"aware":[49],"analysis":[50],"correct":[52],"these":[53],"errors.":[54],"Evaluation":[55],"was":[56],"facilitated":[57],"by":[58],"two":[59],"publicly":[60],"available":[61],"datasets":[62],"from":[63],"TREC-5's":[64],"Confusion":[65],"Track":[66],"containing":[67],"estimated":[68],"error":[69,129],"rates":[70,130],"5%":[72,78,133],"20%":[74,98,135],".":[75],"On":[76,96],"dataset,":[79,99],"we":[80,100],"demonstrate":[81,101],"statistically":[83,103],"significant":[84,104],"improvement":[85,105],"over":[86,106],"prior":[88,114],"art":[89],"Solr's":[91],"mean":[92],"reciprocal":[93],"rank":[94],"(MRR).":[95],"Solr,":[107],"have":[109],"similar":[110],"performance":[111],"art.":[115],"achieves":[119],"MRR":[121],"0.6627":[123],"0.4924":[125],"on":[126],"collections":[127],"with":[128],"approximately":[132],"respectively.":[136]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}