{"id":"https://openalex.org/W2252001897","doi":"https://doi.org/10.3115/v1/w14-0809","title":"Extracting MWEs from Italian corpora: A case study for refining the POS-pattern methodology","display_name":"Extracting MWEs from Italian corpora: A case study for refining the POS-pattern methodology","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252001897","doi":"https://doi.org/10.3115/v1/w14-0809","mag":"2252001897"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0809","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0809","pdf_url":"https://doi.org/10.3115/v1/w14-0809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w14-0809","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040131603","display_name":"Sara Castagnoli","orcid":"https://orcid.org/0000-0002-9308-7242"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sara Castagnoli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040131603"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6912,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88423811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9951000213623047,"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/adjective","display_name":"Adjective","score":0.7580865621566772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333362102508545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6909433007240295},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.6780064105987549},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6365947127342224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6291753649711609},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.5961087346076965},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5548673868179321},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5046418905258179},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.49002230167388916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32214081287384033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15956392884254456},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.09996360540390015}],"concepts":[{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.7580865621566772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333362102508545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6909433007240295},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6780064105987549},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6365947127342224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6291753649711609},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.5961087346076965},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5548673868179321},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5046418905258179},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.49002230167388916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32214081287384033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15956392884254456},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.09996360540390015},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/w14-0809","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0809","pdf_url":"https://doi.org/10.3115/v1/w14-0809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.7813","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.7813","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/W/W14/W14-0809.pdf","raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/397023","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/397023","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:u-pad.unimc.it:11393/241617","is_oa":false,"landing_page_url":"http://hdl.handle.net/11393/241617","pdf_url":null,"source":{"id":"https://openalex.org/S4377196455","display_name":"U-PAD Unimc - Open Digital Publications (University of Macerata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I55133342","host_organization_name":"University of Macerata","host_organization_lineage":["https://openalex.org/I55133342"],"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":{"id":"doi:10.3115/v1/w14-0809","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0809","pdf_url":"https://doi.org/10.3115/v1/w14-0809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W106490349","https://openalex.org/W1529075208","https://openalex.org/W2040049595","https://openalex.org/W2041186695","https://openalex.org/W2127776561","https://openalex.org/W2781679957","https://openalex.org/W3086967371","https://openalex.org/W3150360452"],"related_works":["https://openalex.org/W2011383762","https://openalex.org/W2048414027","https://openalex.org/W2033737867","https://openalex.org/W2024119624","https://openalex.org/W1875133464","https://openalex.org/W2126623367","https://openalex.org/W2387363840","https://openalex.org/W2925146703","https://openalex.org/W2387533774","https://openalex.org/W4285787285"],"abstract_inverted_index":{"An":[0],"established":[1],"method":[2],"for":[3,83,97],"MWE":[4,98],"extrac-tion":[5],"is":[6,23],"the":[7,18,80],"combined":[8],"use":[9],"of":[10,20,68,109],"previously":[11],"iden-tified":[12],"POS-patterns":[13,22,42],"and":[14,47],"association":[15,85,110],"mea-sures.":[16],"However,":[17],"selection":[19],"such":[21],"rarely":[24],"debated.":[25],"Focusing":[26],"on":[27],"Ital-ian":[28],"MWEs":[29],"containing":[30],"at":[31],"least":[32],"one":[33],"adjec-tive,":[34],"we":[35],"set":[36,93],"out":[37],"to":[38,94,102],"explore":[39],"how":[40],"candidate":[41,77],"listed":[43],"in":[44],"relevant":[45],"literature":[46],"lexicographic":[48],"sources":[49],"compare":[50],"with":[51],"POS":[52],"sequences":[53],"exhibited":[54],"by":[55],"statistically":[56],"significant":[57],"n-grams":[58],"including":[59],"an":[60],"adjective":[61],"position":[62],"extracted":[63],"from":[64],"a":[65,90,107],"large":[66],"corpus":[67],"Italian.":[69],"All":[70],"literature-derived":[71],"patterns":[72],"are":[73],"found\u2014and":[74],"new":[75],"meaningful":[76],"pat-terns":[78],"emerge\u2014among":[79],"top-ranking":[81],"tri-grams":[82],"three":[84],"measures.":[86],"We":[87],"conclude":[88],"that":[89],"final":[91],"solid":[92],"be":[95,103],"used":[96],"extraction":[99],"will":[100],"have":[101],"further":[104],"re-fined":[105],"through":[106],"combination":[108],"measures":[111],"as":[112,114],"well":[113],"manual":[115],"inspection.":[116],"1":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}