{"id":"https://openalex.org/W840932241","doi":null,"title":"Unlocking Language Archives Using Search","display_name":"Unlocking Language Archives Using Search","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W840932241","mag":"840932241"},"language":"en","primary_location":{"id":"pmh:oai:escidoc.org:escidoc:1217575","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","pdf_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078981231","display_name":"Herman Stehouwer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210089003","display_name":"Max Planck Institute for Psycholinguistics","ror":"https://ror.org/00671me87","country_code":"NL","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210089003"]}],"countries":["DE","NL"],"is_corresponding":false,"raw_author_name":"Herman Stehouwer","raw_affiliation_strings":["The Language Archive, MPI for Psycholinguistics, Max Planck Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Language Archive, MPI for Psycholinguistics, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210089003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110131226","display_name":"Eric Auer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210089003","display_name":"Max Planck Institute for Psycholinguistics","ror":"https://ror.org/00671me87","country_code":"NL","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210089003"]}],"countries":["DE","NL"],"is_corresponding":false,"raw_author_name":"Eric Auer","raw_affiliation_strings":["The Language Archive, MPI for Psycholinguistics, Max Planck Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Language Archive, MPI for Psycholinguistics, Max Planck Society","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210089003"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1173,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87690549,"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":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2786000072956085,"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":0.2786000072956085,"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/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.25589999556541443,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.2484000027179718,"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/language-archives","display_name":"language archives","score":0.8019999861717224},{"id":"https://openalex.org/keywords/search-mechanisms","display_name":"search mechanisms","score":0.5170000195503235},{"id":"https://openalex.org/keywords/metadata-search","display_name":"metadata search","score":0.7850000262260437},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8069999814033508},{"id":"https://openalex.org/keywords/natural-language-data","display_name":"natural language data","score":0.8029999732971191},{"id":"https://openalex.org/keywords/audio-and-video-data","display_name":"audio and video data","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697206735610962},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7231760025024414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.59831702709198},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5643174648284912},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5548584461212158},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.49856138229370117},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49657613039016724},{"id":"https://openalex.org/C37202355","wikidata":"https://www.wikidata.org/wiki/Q7188071","display_name":"Phrase search","level":5,"score":0.4404897093772888},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43329429626464844},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.4232971668243408},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.3653651475906372},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.35358232259750366},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3026335835456848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21126392483711243},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:escidoc.org:escidoc:1217575","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","pdf_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.8453","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.8453","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-new/W/W11/W11-4104.pdf","raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_1217575","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11858/00-001M-0000-0012-3405-2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Workshop on Language Technologies for Digital Humanities and Cultural Heritage, Hissar, Bulgaria, 16 September 2011","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:840932241","doi":null,"is_oa":false,"landing_page_url":"https://pure.mpg.de/pubman/item/item_1217575_7/component/file_1217573/W11-4104.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:escidoc.org:escidoc:1217575","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","pdf_url":"http://hdl.handle.net/11858/00-001M-0000-0012-3405-2","source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W840932241.pdf","grobid_xml":"https://content.openalex.org/works/W840932241.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W849319502","https://openalex.org/W1500266866","https://openalex.org/W1516789863","https://openalex.org/W1588867110","https://openalex.org/W1590147869","https://openalex.org/W2031388750","https://openalex.org/W2134735375","https://openalex.org/W2145565586","https://openalex.org/W2167962590","https://openalex.org/W2171950509","https://openalex.org/W2759311441"],"related_works":["https://openalex.org/W2980385832","https://openalex.org/W847570047","https://openalex.org/W7160525935","https://openalex.org/W7115229537","https://openalex.org/W3031403173","https://openalex.org/W2276617460","https://openalex.org/W1986786314","https://openalex.org/W1958251184","https://openalex.org/W7029475000","https://openalex.org/W7098410673"],"abstract_inverted_index":{"The":[0],"Language":[1],"Archive":[2],"manages":[3],"one":[4],"of":[5,12,19,35,91],"the":[6,68,92],"largest":[7],"and":[8,21,48,54,65,71],"most":[9],"varied":[10],"sets":[11],"natural":[13],"language":[14],"data.":[15],"This":[16,83],"data":[17,46],"consists":[18],"video":[20],"audio":[22],"enriched":[23],"with":[24,96],"annotations.":[25],"It":[26],"is":[27],"available":[28,93],"for":[29,78],"more":[30,80],"than":[31],"250":[32],"languages,":[33],"many":[34],"which":[36,61],"are":[37],"endangered.":[38],"Researchers":[39],"have":[40,62],"a":[41,79,88,97,104],"need":[42],"to":[43,57,86],"access":[44],"this":[45,59],"conveniently":[47],"efficiently.":[49],"We":[50],"provide":[51,87],"several":[52],"browse":[53],"search":[55,73,94],"methods":[56,74],"cover":[58],"need,":[60],"been":[63],"developed":[64],"expanded":[66],"over":[67],"years.":[69],"Metadata":[70],"content-oriented":[72],"can":[75],"be":[76],"connected":[77],"focused":[81],"search.":[82],"article":[84],"aims":[85],"complete":[89],"overview":[90],"mechanisms,":[95],"focus":[98],"on":[99],"annotation":[100],"content":[101],"search,":[102],"including":[103],"benchmark.":[105],"1":[106]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}
