{"id":"https://openalex.org/W3083414057","doi":"https://doi.org/10.1145/3409256.3409827","title":"Optimizing Hyper-Phrase Queries","display_name":"Optimizing Hyper-Phrase Queries","publication_year":2020,"publication_date":"2020-09-05","ids":{"openalex":"https://openalex.org/W3083414057","doi":"https://doi.org/10.1145/3409256.3409827","mag":"3083414057"},"language":"en","primary_location":{"id":"doi:10.1145/3409256.3409827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409256.3409827","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409256.3409827","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3409256.3409827","any_repository_has_fulltext":null},"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":["Max Planck Institute for Informatics, Saarbruecken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, 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/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"]},{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Berberich","raw_affiliation_strings":["Max Planck Institute for Informatics & Saarbruecken University of Applied Sciences (htw saar), Saarbruecken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics & Saarbruecken University of Applied Sciences (htw saar), Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210120512","https://openalex.org/I4210109712"]}]}],"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":0.1353,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.560182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199310302734375},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.810380220413208},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5552932024002075},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4708644449710846},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46211081743240356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.389125257730484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3673921823501587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199310302734375},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.810380220413208},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5552932024002075},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4708644449710846},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46211081743240356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.389125257730484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3673921823501587},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3409256.3409827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409256.3409827","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409256.3409827","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_3287014","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0008-0335-9","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":"ICTIR '20","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3409256.3409827","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3409256.3409827","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3409256.3409827","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083414057.pdf","grobid_xml":"https://content.openalex.org/works/W3083414057.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W59640500","https://openalex.org/W59952361","https://openalex.org/W1981732427","https://openalex.org/W1984614894","https://openalex.org/W1986079495","https://openalex.org/W2004194663","https://openalex.org/W2028258439","https://openalex.org/W2029576182","https://openalex.org/W2103224511","https://openalex.org/W2113618143","https://openalex.org/W2123442489","https://openalex.org/W2129055634","https://openalex.org/W2140453381","https://openalex.org/W2150052577","https://openalex.org/W2153329411","https://openalex.org/W2157306707","https://openalex.org/W2489511000","https://openalex.org/W2908045038","https://openalex.org/W2946046356","https://openalex.org/W3004540582","https://openalex.org/W3158986179","https://openalex.org/W4300007198","https://openalex.org/W6602412471","https://openalex.org/W6723023213","https://openalex.org/W7014932365","https://openalex.org/W7029218844"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W2033009170","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W4255446307","https://openalex.org/W4245925686"],"abstract_inverted_index":{"A":[0],"hyper-phrase":[1],"query":[2,43,72],"(HPQ)":[3],"consists":[4],"of":[5,8,25,58,71,90],"a":[6],"sequence":[7],"phrase":[9],"sets.":[10],"Such":[11],"queries":[12],"naturally":[13],"arise":[14],"when":[15],"attempting":[16],"to":[17,32,45,53,78,102],"spot":[18],"knowledge":[19],"graph":[20],"(KG)":[21],"facts":[22,27,95],"or":[23],"sets":[24],"KG":[26],"in":[28,49,65,98],"large":[29],"document":[30,99],"collections":[31,100],"establish":[33],"their":[34],"provenance.":[35],"Our":[36],"approach":[37],"addresses":[38],"this":[39],"challenge":[40],"by":[41],"proposing":[42],"operators":[44,73],"detect":[46],"text":[47,81],"regions":[48,82],"documents":[50],"that":[51,74],"correspond":[52],"the":[54,67,80,84,88],"HPQ":[55],"as":[56],"combinations":[57],"n-grams":[59],"and":[60],"skip-grams.":[61],"The":[62],"optimization":[63],"lies":[64],"identifying":[66],"most":[68],"cost-efficient":[69],"order":[70],"can":[75],"be":[76],"executed":[77],"identify":[79],"containing":[83],"HPQ.":[85],"We":[86],"show":[87],"efficiency":[89],"our":[91],"optimizations":[92],"on":[93],"spotting":[94],"from":[96],"Wikidata":[97],"amounting":[101],"more":[103],"than":[104],"thirty":[105],"million":[106],"documents.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}