{"id":"https://openalex.org/W2908045038","doi":"https://doi.org/10.1145/3289600.3290618","title":"Structured Search in Annotated Document Collections","display_name":"Structured Search in Annotated Document Collections","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2908045038","doi":"https://doi.org/10.1145/3289600.3290618","mag":"2908045038"},"language":"en","primary_location":{"id":"doi:10.1145/3289600.3290618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3290618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","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/A5101456958","display_name":"Dhruv Gupta","orcid":"https://orcid.org/0009-0008-6364-482X"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dhruv Gupta","raw_affiliation_strings":["Saarbr\u00fccken Graduate School of Computer Science Saarland Informatics Campus, Saarbruecken, Germany"],"affiliations":[{"raw_affiliation_string":"Saarbr\u00fccken Graduate School of Computer Science Saarland Informatics Campus, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039440854","display_name":"Klaus Berberich","orcid":"https://orcid.org/0000-0003-3813-9721"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Berberich","raw_affiliation_strings":["Saarland Informatics Campus, Saarbruecken, Germany"],"affiliations":[{"raw_affiliation_string":"Saarland Informatics Campus, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101456958"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54886348,"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":"794","last_page":"797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T12090","display_name":"Language and cultural evolution","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8281374573707581},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.809712290763855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6570490598678589},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.534231424331665},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4868861734867096},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4716963768005371},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4699164927005768},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.4233306646347046},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.41977500915527344},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4131827652454376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.410391628742218},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3576129078865051},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12151312828063965},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0748671293258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281374573707581},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.809712290763855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6570490598678589},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.534231424331665},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4868861734867096},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4716963768005371},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4699164927005768},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.4233306646347046},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.41977500915527344},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4131827652454376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.410391628742218},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3576129078865051},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12151312828063965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0748671293258667},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3289600.3290618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3289600.3290618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_3014381","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0002-A8D6-F","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2004194663","https://openalex.org/W2020589513","https://openalex.org/W2021682442","https://openalex.org/W2122494037","https://openalex.org/W2394797107","https://openalex.org/W2565888713","https://openalex.org/W2612728726","https://openalex.org/W2897630003"],"related_works":["https://openalex.org/W1984061923","https://openalex.org/W2359166167","https://openalex.org/W3590553","https://openalex.org/W3110844189","https://openalex.org/W1976839151","https://openalex.org/W2336826532","https://openalex.org/W3040185272","https://openalex.org/W2373953901","https://openalex.org/W2214614887","https://openalex.org/W2169669347"],"abstract_inverted_index":{"In":[0,43],"this":[1],"work,":[2],"we":[3,47,78],"demonstrate":[4,70],"structured":[5,30,75],"search":[6,22,76],"capabilities":[7,77],"of":[8,60],"the":[9,58],"GYANI":[10,13],"indexing":[11],"infrastructure.":[12],"allows":[14],"linguists,":[15],"journalists,":[16],"and":[17,41,66,93],"scholars":[18],"in":[19,28,57],"humanities":[20],"to":[21,45,53],"large":[23],"semantically":[24],"annotated":[25,82],"document":[26],"collections":[27],"a":[29],"manner":[31],"by":[32,72],"supporting":[33],"queries":[34],"with":[35],"regular":[36],"expressions":[37],"between":[38],"word":[39],"sequences":[40],"annotations.":[42],"addition":[44],"this,":[46],"provide":[48],"support":[49],"for":[50,85],"attaching":[51],"semantics":[52],"words":[54],"via":[55],"annotations":[56],"form":[59],"part-of-speech,":[61],"named":[62],"entities,":[63],"temporal":[64],"expressions,":[65],"numerical":[67],"quantities.":[68],"We":[69],"that":[71],"enabling":[73],"such":[74,89],"can":[79],"quickly":[80],"gather":[81],"text":[83],"regions":[84],"various":[86],"knowledge-centric":[87],"tasks":[88],"as":[90],"information":[91],"extraction":[92],"question":[94],"answering.":[95]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
