{"id":"https://openalex.org/W2892658594","doi":"https://doi.org/10.15439/2018f186","title":"Automatic Extraction of Synonymous Collocation Pairs from a Text Corpus","display_name":"Automatic Extraction of Synonymous Collocation Pairs from a Text Corpus","publication_year":2018,"publication_date":"2018-09-26","ids":{"openalex":"https://openalex.org/W2892658594","doi":"https://doi.org/10.15439/2018f186","mag":"2892658594"},"language":"en","primary_location":{"id":"doi:10.15439/2018f186","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2018f186","pdf_url":"https://annals-csis.org/proceedings/2018/drp/pdf/186.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2018/drp/pdf/186.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081869570","display_name":"Nina Khairova","orcid":"https://orcid.org/0000-0002-9826-0286"},"institutions":[{"id":"https://openalex.org/I67256668","display_name":"National Technical University \"Kharkiv Polytechnic Institute\"","ror":"https://ror.org/00yp5c433","country_code":"UA","type":"education","lineage":["https://openalex.org/I67256668"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Nina Khairova","raw_affiliation_strings":["National Technical University \"Kharkiv Polytechnic Institute\", Kyrpychova str., 61002, Kharkiv, Ukraine"],"affiliations":[{"raw_affiliation_string":"National Technical University \"Kharkiv Polytechnic Institute\", Kyrpychova str., 61002, Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061829636","display_name":"Svitlana Petrasova","orcid":"https://orcid.org/0000-0001-6011-135X"},"institutions":[{"id":"https://openalex.org/I67256668","display_name":"National Technical University \"Kharkiv Polytechnic Institute\"","ror":"https://ror.org/00yp5c433","country_code":"UA","type":"education","lineage":["https://openalex.org/I67256668"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Svitlana Petrasova","raw_affiliation_strings":["National Technical University \"Kharkiv Polytechnic Institute\", Kyrpychova str., 61002, Kharkiv, Ukraine"],"affiliations":[{"raw_affiliation_string":"National Technical University \"Kharkiv Polytechnic Institute\", Kyrpychova str., 61002, Kharkiv, Ukraine","institution_ids":["https://openalex.org/I67256668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056656799","display_name":"W\u0142odzimierz Lewoniewski","orcid":"https://orcid.org/0000-0002-0163-5492"},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"W\u0142odzimierz Lewoniewski","raw_affiliation_strings":["Pozna University of Economics and Business, Al. Niepodlegci 10, 61-875 Pozna","Pozna\u0144 University of Economics and Business, Al. Niepodleg\u0142\u015bci 10, 61-875 Pozna\u0144"],"affiliations":[{"raw_affiliation_string":"Pozna University of Economics and Business, Al. Niepodlegci 10, 61-875 Pozna","institution_ids":["https://openalex.org/I12379730"]},{"raw_affiliation_string":"Pozna\u0144 University of Economics and Business, Al. Niepodleg\u0142\u015bci 10, 61-875 Pozna\u0144","institution_ids":["https://openalex.org/I12379730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439047","display_name":"\u041erken Mamyrbayev","orcid":"https://orcid.org/0000-0001-8318-3794"},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Orken Mamyrbayev","raw_affiliation_strings":["Institute of Information and Computational Technologies, 125, Pushkin str., 050010, Almaty, Republic of Kazakhstan"],"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, 125, Pushkin str., 050010, Almaty, Republic of Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043074342","display_name":"Kuralai Mukhsina","orcid":null},"institutions":[{"id":"https://openalex.org/I185571130","display_name":"Al-Farabi Kazakh National University","ror":"https://ror.org/03q0vrn42","country_code":"KZ","type":"education","lineage":["https://openalex.org/I185571130"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Kuralai Mukhsina","raw_affiliation_strings":["Al-Farabi Kazakh National University, Kazakhstan, 71 al-Farabi Ave., Almaty, Republic of Kazakhstan,"],"affiliations":[{"raw_affiliation_string":"Al-Farabi Kazakh National University, Kazakhstan, 71 al-Farabi Ave., Almaty, Republic of Kazakhstan,","institution_ids":["https://openalex.org/I185571130"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081869570"],"corresponding_institution_ids":["https://openalex.org/I67256668"],"apc_list":null,"apc_paid":null,"fwci":0.3129,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67133281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":null,"first_page":"485","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.996999979019165,"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/T13629","display_name":"Text Readability and Simplification","score":0.996999979019165,"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":0.6900948286056519},{"id":"https://openalex.org/keywords/collocation","display_name":"Collocation (remote sensing)","score":0.681790292263031},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.587336003780365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49548614025115967},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.49408963322639465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14232057332992554},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08145749568939209},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05669909715652466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900948286056519},{"id":"https://openalex.org/C80023036","wikidata":"https://www.wikidata.org/wiki/Q5147531","display_name":"Collocation (remote sensing)","level":2,"score":0.681790292263031},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.587336003780365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49548614025115967},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.49408963322639465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14232057332992554},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08145749568939209},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05669909715652466}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.15439/2018f186","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2018f186","pdf_url":"https://annals-csis.org/proceedings/2018/drp/pdf/186.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:5171cfa4fb974f199f4edd794aa22b22","is_oa":true,"landing_page_url":"https://doaj.org/article/5171cfa4fb974f199f4edd794aa22b22","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 15, Pp 485-488 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2018f186","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2018f186","pdf_url":"https://annals-csis.org/proceedings/2018/drp/pdf/186.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G3328075582","display_name":null,"funder_award_id":"project No. AP05131073","funder_id":"https://openalex.org/F4320322726","funder_display_name":"Ministry of Education and Science of the Republic of Kazakhstan"}],"funders":[{"id":"https://openalex.org/F4320322726","display_name":"Ministry of Education and Science of the Republic of Kazakhstan","ror":"https://ror.org/03pj6ge82"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892658594.pdf","grobid_xml":"https://content.openalex.org/works/W2892658594.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W156229664","https://openalex.org/W1549339229","https://openalex.org/W1980776243","https://openalex.org/W2011358768","https://openalex.org/W2028742638","https://openalex.org/W2107130271","https://openalex.org/W2108869098","https://openalex.org/W2130571329","https://openalex.org/W2188648436","https://openalex.org/W2251044566","https://openalex.org/W2251291469","https://openalex.org/W2579343286","https://openalex.org/W2579947676","https://openalex.org/W2614620964","https://openalex.org/W2759855257","https://openalex.org/W2766484160","https://openalex.org/W4381304672","https://openalex.org/W6606311278","https://openalex.org/W6691444529"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2370840338","https://openalex.org/W2388641108","https://openalex.org/W2368317224","https://openalex.org/W2370651559","https://openalex.org/W3000494655","https://openalex.org/W2383177152","https://openalex.org/W3000893075","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Automatic":[0],"extraction":[1],"of":[2,13,20,37,39,60,70,87,122,129],"synonymous":[3,68,74,113,130],"collocation":[4],"pairs":[5],"from":[6,102],"text":[7],"corpora":[8],"is":[9],"a":[10,98,103],"challenging":[11],"task":[12],"NLP.":[14],"In":[15],"order":[16],"to":[17,66,141],"search":[18,132],"collocations":[19,44,114,131],"similar":[21],"meaning":[22],"in":[23,116,133],"English":[24],"texts,":[25,117],"we":[26,55],"use":[27],"logical-algebraic":[28],"equations.":[29,91],"These":[30],"equations":[31],"combine":[32],"grammatical":[33,58,83],"and":[34,42,50,84],"semantic":[35,85],"characteristics":[36,59,86],"words":[38,69],"substantive,":[40],"attributive":[41],"verbal":[43],"types.":[45],"With":[46],"Stanford":[47,51],"POS":[48],"tagger":[49],"Universal":[52],"Dependencies":[53],"parser,":[54],"identify":[56],"the":[57,88,110,118,123,138],"words.":[61],"We":[62],"exploit":[63],"WordNet":[64],"synsets":[65],"pick":[67],"collocations.":[71],"The":[72,106,127],"potential":[73],"word":[75],"combinations":[76],"found":[77],"are":[78],"checked":[79],"for":[80],"compliance":[81],"with":[82],"proposed":[89],"logical-linguistic":[90],"Our":[92],"dataset":[93],"includes":[94],"more":[95,111,119],"than":[96],"half":[97],"million":[99],"Wikipedia":[100],"articles":[101],"few":[104],"portals.":[105],"experiment":[107,135],"shows":[108],"that":[109],"frequent":[112],"occur":[115],"related":[120],"topics":[121],"texts":[124],"might":[125],"be.":[126],"precision":[128],"our":[134],"has":[136],"achieved":[137],"results":[139],"close":[140],"other":[142],"studies":[143],"like":[144],"ours.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
