{"id":"https://openalex.org/W3135647274","doi":"https://doi.org/10.3390/make3010013","title":"Leaving No Stone Unturned: Flexible Retrieval of Idiomatic Expressions from a Large Text Corpus","display_name":"Leaving No Stone Unturned: Flexible Retrieval of Idiomatic Expressions from a Large Text Corpus","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3135647274","doi":"https://doi.org/10.3390/make3010013","mag":"3135647274"},"language":"en","primary_location":{"id":"doi:10.3390/make3010013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make3010013","pdf_url":"https://www.mdpi.com/2504-4990/3/1/13/pdf?version=1614767330","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/3/1/13/pdf?version=1614767330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032619089","display_name":"Callum Hughes","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Callum Hughes","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013619071","display_name":"Maxim Filimonov","orcid":"https://orcid.org/0000-0002-3144-9252"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maxim Filimonov","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK"],"raw_orcid":"https://orcid.org/0000-0002-3144-9252","affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059871403","display_name":"Alison Wray","orcid":"https://orcid.org/0000-0002-2144-4458"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alison Wray","raw_affiliation_strings":["School of English, Communication and Philosophy, Cardiff University, Cardiff CF10 3EU, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of English, Communication and Philosophy, Cardiff University, Cardiff CF10 3EU, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016345745","display_name":"\u202aIrena Spasi\u0107","orcid":"https://orcid.org/0000-0002-8132-3885"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Irena Spasi\u0107","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK"],"raw_orcid":"https://orcid.org/0000-0002-8132-3885","affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016345745"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.4197,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67854521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"3","issue":"1","first_page":"263","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9957000017166138,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9957000017166138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8198236227035522},{"id":"https://openalex.org/keywords/adverbial","display_name":"Adverbial","score":0.6146867871284485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.609370231628418},{"id":"https://openalex.org/keywords/inflection","display_name":"Inflection","score":0.5648201107978821},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5126270651817322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512169599533081},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5101675987243652},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5045334100723267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4375925362110138},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41065818071365356},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3327217102050781},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12087279558181763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198236227035522},{"id":"https://openalex.org/C2779357210","wikidata":"https://www.wikidata.org/wiki/Q380012","display_name":"Adverbial","level":2,"score":0.6146867871284485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.609370231628418},{"id":"https://openalex.org/C159403335","wikidata":"https://www.wikidata.org/wiki/Q207857","display_name":"Inflection","level":2,"score":0.5648201107978821},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5126270651817322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512169599533081},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5101675987243652},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5045334100723267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4375925362110138},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41065818071365356},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3327217102050781},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12087279558181763},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/make3010013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make3010013","pdf_url":"https://www.mdpi.com/2504-4990/3/1/13/pdf?version=1614767330","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:138986","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:42e53744b8d14b69b46d6544e871b48a","is_oa":true,"landing_page_url":"https://doaj.org/article/42e53744b8d14b69b46d6544e871b48a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Machine Learning and Knowledge Extraction, Vol 3, Iss 1, Pp 263-283 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-4990/3/1/13/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/make3010013","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction; Volume 3; Issue 1; Pages: 263-283","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make3010013","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make3010013","pdf_url":"https://www.mdpi.com/2504-4990/3/1/13/pdf?version=1614767330","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135647274.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W172541218","https://openalex.org/W1502101714","https://openalex.org/W1503951804","https://openalex.org/W1719006806","https://openalex.org/W1979773093","https://openalex.org/W2015933299","https://openalex.org/W2021332569","https://openalex.org/W2032956935","https://openalex.org/W2053154970","https://openalex.org/W2079004251","https://openalex.org/W2079547420","https://openalex.org/W2081580037","https://openalex.org/W2082179583","https://openalex.org/W2098162425","https://openalex.org/W2101547548","https://openalex.org/W2104246439","https://openalex.org/W2118202495","https://openalex.org/W2120578583","https://openalex.org/W2124482566","https://openalex.org/W2141179513","https://openalex.org/W2165897980","https://openalex.org/W2178314882","https://openalex.org/W2339709765","https://openalex.org/W2517996181","https://openalex.org/W2750867747","https://openalex.org/W2760314189","https://openalex.org/W2770760637","https://openalex.org/W2786226395","https://openalex.org/W2806311394","https://openalex.org/W2889108838","https://openalex.org/W2889649307","https://openalex.org/W2963355447","https://openalex.org/W3031968991","https://openalex.org/W4206813637","https://openalex.org/W4250317401","https://openalex.org/W4252076394","https://openalex.org/W4388119441","https://openalex.org/W6704009123"],"related_works":["https://openalex.org/W4283816871","https://openalex.org/W2360850911","https://openalex.org/W2908487582","https://openalex.org/W2368780771","https://openalex.org/W2291484421","https://openalex.org/W2358076931","https://openalex.org/W48803033","https://openalex.org/W2369761896","https://openalex.org/W2388579645","https://openalex.org/W2373689996"],"abstract_inverted_index":{"Idioms":[0],"are":[1,59],"multi-word":[2],"expressions":[3],"whose":[4],"meaning":[5,13],"cannot":[6],"always":[7],"be":[8],"deduced":[9],"from":[10,42,78],"the":[11,104,112,185,217,226,235,243],"literal":[12],"of":[14,20,32,116,132,137,155,163,174,181,184,193,222,231,234,257],"constituent":[15],"words.":[16],"A":[17],"key":[18],"feature":[19],"idioms":[21,175,259],"that":[22,95,209],"is":[23,28,176],"central":[24],"to":[25,74,109,241],"this":[26],"paper":[27],"their":[29,40,188],"peculiar":[30],"mixture":[31],"fixedness":[33],"and":[34,127,204,212,224,248,254,276],"variability,":[35],"which":[36],"poses":[37],"challenges":[38,50],"for":[39,89,111],"retrieval":[41,85,173],"large":[43,261],"corpora":[44],"using":[45],"traditional":[46],"search":[47,93,170,186,219,228],"approaches.":[48],"These":[49],"hinder":[51],"insights":[52],"into":[53,190],"idiom":[54,75,117,138],"usage,":[55],"affecting":[56],"users":[57],"who":[58],"conducting":[60],"linguistic":[61,182],"research":[62],"as":[63,65,149,151,272],"well":[64,150],"those":[66],"involved":[67],"in":[68,100,197,220,229,260,269],"language":[69,200,274,278],"education.":[70],"To":[71],"facilitate":[72,266],"access":[73],"examples":[76],"taken":[77],"real-world":[79],"contexts,":[80],"we":[81],"introduce":[82],"an":[83,97,165,206],"information":[84],"system":[86,105,158,215],"designed":[87],"specifically":[88],"idioms.":[90],"Given":[91],"a":[92,130,179,191,198,252],"query":[94,133,194,199],"represents":[96],"idiom,":[98],"typically":[99],"its":[101],"canonical":[102],"form,":[103],"expands":[106],"it":[107],"automatically":[108],"account":[110],"most":[113],"common":[114],"types":[115,136,154],"variation":[118,139],"including":[119],"inflection,":[120],"open":[121],"slots,":[122],"adjectival":[123],"or":[124],"adverbial":[125],"modification":[126],"passivisation.":[128],"As":[129],"by-product":[131],"expansion,":[134],"other":[135,152],"captured":[140],"include":[141],"derivation,":[142],"compounding,":[143],"negation,":[144],"distribution":[145],"across":[146],"multiple":[147],"clauses":[148,195],"unforeseen":[153],"variation.":[156],"The":[157],"was":[159,239],"implemented":[160],"on":[161],"top":[162],"Elasticsearch,":[164],"open-source,":[166],"distributed,":[167],"scalable,":[168],"real-time":[169],"engine.":[171],"Flexible":[172],"supported":[177],"by":[178],"combination":[180],"pre-processing":[183],"queries,":[187],"translation":[189],"set":[192],"written":[196],"called":[201],"Query":[202],"DSL,":[203],"analysis,":[205],"indexing":[207],"process":[208],"involves":[210],"tokenisation":[211],"normalisation.":[213],"Our":[214],"outperformed":[216,225],"phrase":[218],"terms":[221,230],"recall":[223],"keyword":[227],"precision.":[232],"Out":[233],"three,":[236],"our":[237,263],"approach":[238,264],"found":[240],"provide":[242],"best":[244],"balance":[245],"between":[246],"precision":[247],"recall.":[249],"By":[250],"providing":[251],"fast":[253],"easy":[255],"way":[256],"finding":[258],"corpora,":[262],"can":[265],"further":[267],"developments":[268],"fields":[270],"such":[271],"linguistics,":[273],"education":[275],"natural":[277],"processing.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}