{"id":"https://openalex.org/W3183379259","doi":"https://doi.org/10.18653/v1/2021.mwe-1.3","title":"Data-driven Identification of Idioms in Song Lyrics","display_name":"Data-driven Identification of Idioms in Song Lyrics","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3183379259","doi":"https://doi.org/10.18653/v1/2021.mwe-1.3","mag":"3183379259"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.mwe-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.3","pdf_url":"https://aclanthology.org/2021.mwe-1.3.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2021.mwe-1.3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062377005","display_name":"Miriam Amin","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Miriam Amin","raw_affiliation_strings":["Leipzig University, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leipzig University, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037943398","display_name":"P\u00e9ter Fankhauser","orcid":"https://orcid.org/0000-0001-7128-9188"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Fankhauser","raw_affiliation_strings":["Leibniz Institute For The German Language, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute For The German Language, Mannheim, Germany","institution_ids":["https://openalex.org/I4210099471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065768650","display_name":"Marc Kupietz","orcid":"https://orcid.org/0000-0001-8997-8256"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Kupietz","raw_affiliation_strings":["Leibniz Institute For The German Language, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute For The German Language, Mannheim, Germany","institution_ids":["https://openalex.org/I4210099471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076549048","display_name":"Roman Schneider","orcid":"https://orcid.org/0000-0002-6375-530X"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roman Schneider","raw_affiliation_strings":["Leibniz Institute For The German Language, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute For The German Language, Mannheim, Germany","institution_ids":["https://openalex.org/I4210099471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67839377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9898999929428101,"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":0.9828000068664551,"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":0.8560140132904053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6938237547874451},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6719342470169067},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6353563070297241},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.6231070160865784},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.5663560628890991},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.43180787563323975},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.41673266887664795},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23608651757240295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560140132904053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6938237547874451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6719342470169067},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6353563070297241},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.6231070160865784},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.5663560628890991},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.43180787563323975},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.41673266887664795},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23608651757240295},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2021.mwe-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.3","pdf_url":"https://aclanthology.org/2021.mwe-1.3.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:ids-pub.bsz-bw.de:10682","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bsz:mh39-106825","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"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":"","raw_type":"conferenceobject"},{"id":"pmh:oai:publica.fraunhofer.de:publica/416984","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/416984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.mwe-1.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.mwe-1.3","pdf_url":"https://aclanthology.org/2021.mwe-1.3.pdf","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 17th Workshop on Multiword Expressions (MWE 2021)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3183379259.pdf","grobid_xml":"https://content.openalex.org/works/W3183379259.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W40123913","https://openalex.org/W991530533","https://openalex.org/W1498763386","https://openalex.org/W1548461347","https://openalex.org/W1592343866","https://openalex.org/W2021034890","https://openalex.org/W2046201573","https://openalex.org/W2074228526","https://openalex.org/W2079547420","https://openalex.org/W2083199601","https://openalex.org/W2084053452","https://openalex.org/W2125031621","https://openalex.org/W2153579005","https://openalex.org/W2156672590","https://openalex.org/W2224490803","https://openalex.org/W2250493249","https://openalex.org/W2296194829","https://openalex.org/W2402668809","https://openalex.org/W2475487531","https://openalex.org/W2502430711","https://openalex.org/W2517996181","https://openalex.org/W2592228903","https://openalex.org/W2664496537","https://openalex.org/W2740606975","https://openalex.org/W2752672336","https://openalex.org/W2793082239","https://openalex.org/W2897500967","https://openalex.org/W2900735439","https://openalex.org/W2903145900","https://openalex.org/W2921492024","https://openalex.org/W3001969633","https://openalex.org/W3028630122","https://openalex.org/W3045510483","https://openalex.org/W3118354424","https://openalex.org/W3119135819","https://openalex.org/W4292550923","https://openalex.org/W4294170691","https://openalex.org/W4301691548"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W2389838651","https://openalex.org/W2597614303","https://openalex.org/W437317580","https://openalex.org/W3214861561","https://openalex.org/W3095531775","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W2889302474"],"abstract_inverted_index":{"The":[0],"automatic":[1],"recognition":[2],"of":[3,53,66,80,97,115,138,144],"idioms":[4,139],"poses":[5],"a":[6,64,88,95,106,142],"challenging":[7],"problem":[8],"for":[9,37,68,117],"NLP":[10],"applications.":[11],"Whereas":[12],"native":[13],"speakers":[14],"can":[15,47],"intuitively":[16],"handle":[17],"multiword":[18],"expressions":[19],"whose":[20],"compositional":[21],"meanings":[22],"are":[23],"hard":[24],"to":[25,28,110],"trace":[26],"back":[27],"individual":[29,113],"word":[30],"semantics,":[31],"there":[32],"is":[33],"still":[34],"ample":[35],"scope":[36],"improvement":[38],"regarding":[39],"computational":[40],"approaches.":[41],"We":[42,83],"assume":[43],"that":[44],"idiomatic":[45],"constructions":[46],"be":[48],"characterized":[49],"by":[50],"gradual":[51],"intensities":[52],"semantic":[54],"non-compositionality,":[55],"formal":[56],"fixedness,":[57],"and":[58,62,73,121,127],"unusual":[59],"usage":[60],"context,":[61],"introduce":[63],"number":[65],"measures":[67,76,79],"these":[69],"characteristics,":[70],"comprising":[71],"count-based":[72],"predictive":[74],"collocation":[75],"together":[77],"with":[78],"context":[81],"(un)similarity.":[82],"evaluate":[84,131],"our":[85],"approach":[86],"on":[87,134],"manually":[89],"labelled":[90],"gold":[91],"standard,":[92],"derived":[93],"from":[94,141],"corpus":[96],"German":[98],"pop":[99],"lyrics.":[100],"To":[101],"this":[102],"end,":[103],"we":[104,130],"apply":[105],"Random":[107],"Forest":[108],"classifier":[109,133],"analyze":[111],"the":[112,123,132],"contribution":[114],"features":[116],"automatically":[118],"detecting":[119],"idioms,":[120,146],"study":[122],"trade-off":[124],"between":[125],"recall":[126],"precision.":[128],"Finally,":[129],"an":[135],"independent":[136],"dataset":[137],"extracted":[140],"list":[143],"Wikipedia":[145],"achieving":[147],"state-of-the":[148],"art":[149],"accuracy.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
