{"id":"https://openalex.org/W7117645314","doi":"https://doi.org/10.1145/3773274.3774668","title":"Unsupervised Term Extraction in Highly Technical Domains: Models and Datasets for Low-Resource Kazakh and English Languages","display_name":"Unsupervised Term Extraction in Highly Technical Domains: Models and Datasets for Low-Resource Kazakh and English Languages","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7117645314","doi":"https://doi.org/10.1145/3773274.3774668"},"language":null,"primary_location":{"id":"doi:10.1145/3773274.3774668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773274.3774668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011115168","display_name":"Aiganym Mansurova","orcid":"https://orcid.org/0009-0007-9076-0722"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aiganym Mansurova","raw_affiliation_strings":["Astana IT University, Astana, Kazakhstan","Astana IT University,, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0007-9076-0722","affiliations":[{"raw_affiliation_string":"Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]},{"raw_affiliation_string":"Astana IT University,, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092706663","display_name":"Aigerim Mansurova","orcid":"https://orcid.org/0009-0003-1978-9574"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aigerim Mansurova","raw_affiliation_strings":["Astana IT University, Astana, Kazakhstan","Astana IT University,, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0003-1978-9574","affiliations":[{"raw_affiliation_string":"Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]},{"raw_affiliation_string":"Astana IT University,, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117383138","display_name":"Aliya Kalykulova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aliya Kalykulova","raw_affiliation_strings":["Astana IT University,, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0006-5641-3797","affiliations":[{"raw_affiliation_string":"Astana IT University,, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092405032","display_name":"Almas Alzhanov","orcid":"https://orcid.org/0009-0007-8083-2366"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Almas Alzhanov","raw_affiliation_strings":["Astana IT University,, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0007-8083-2366","affiliations":[{"raw_affiliation_string":"Astana IT University,, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121685961","display_name":"Yermek Alimzhanov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Yermek Alimzhanov","raw_affiliation_strings":["Astana IT University,, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-8758-2220","affiliations":[{"raw_affiliation_string":"Astana IT University,, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076371700","display_name":"Yerzhan Baiburin","orcid":"https://orcid.org/0000-0002-1583-9912"},"institutions":[{"id":"https://openalex.org/I4210096915","display_name":"Sarsen Amanzholov East Kazakhstan University","ror":"https://ror.org/00vj0q898","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210096915"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Yerzhan Baiburin","raw_affiliation_strings":["Amanzholov East Kazakhstan State University, Ust-Kamenogorsk, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-1583-9912","affiliations":[{"raw_affiliation_string":"Amanzholov East Kazakhstan State University, Ust-Kamenogorsk, Kazakhstan","institution_ids":["https://openalex.org/I4210096915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088617921","display_name":"Aliya Nugumanova","orcid":"https://orcid.org/0000-0001-5522-4421"},"institutions":[{"id":"https://openalex.org/I4210141757","display_name":"Astana Medical University","ror":"https://ror.org/038mavt60","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210141757"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aliya Nugumanova","raw_affiliation_strings":["Astana IT University, Astana, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-5522-4421","affiliations":[{"raw_affiliation_string":"Astana IT University, Astana, Kazakhstan","institution_ids":["https://openalex.org/I4210141757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58467308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.31220000982284546,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.31220000982284546,"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"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.2248000055551529,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.1225999966263771,"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/terminology","display_name":"Terminology","score":0.6639999747276306},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.6625000238418579},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.521399974822998},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.43140000104904175},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4311000108718872},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4065999984741211},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3646000027656555},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785099983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7084000110626221},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6639999747276306},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.43140000104904175},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C2780617661","wikidata":"https://www.wikidata.org/wiki/Q541563","display_name":"Subcategory","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773274.3774668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3773274.3774668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6286564469337463}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2962903510","https://openalex.org/W4224302157","https://openalex.org/W4385573066","https://openalex.org/W4410711748"],"related_works":[],"abstract_inverted_index":{"The":[0,90],"paper":[1],"presents":[2],"a":[3,26,46,102],"framework":[4],"for":[5,96],"bilingual":[6],"terminology":[7,106],"extraction":[8],"targeting":[9],"highly":[10],"technical":[11],"domains":[12],"and":[13,24,49,62,67,100,108],"the":[14,68],"low-resource":[15],"Kazakh":[16,50],"language.":[17],"We":[18,42],"develop":[19],"two":[20],"unsupervised":[21,98],"term":[22],"annotators":[23],"introduce":[25],"hybrid":[27],"Semantic":[28],"NMF":[29],"model":[30],"that":[31],"combines":[32],"non-negative":[33],"matrix":[34],"factorization":[35],"with":[36],"multilingual":[37],"embeddings":[38],"(LaBSE,":[39],"E5-base,":[40],"BGE-M3).":[41],"further":[43],"release":[44],"Matcha,":[45],"BIO-annotated":[47],"English":[48],"corpus":[51],"(~3k":[52],"terms)":[53],"to":[54,75,105],"fine-tune":[55],"supervised":[56,79,81],"extractors":[57],"(BERT-BiLSTM-CRF,":[58],"XLM-RoBERTa).":[59],"Across":[60],"ACTER":[61],"ACL":[63],"RD-TEC":[64],"2.0":[65],"benchmarks":[66],"new":[69],"Matcha":[70],"corpus,":[71],"UA2":[72],"attains":[73],"up":[74],"51.8%":[76],"F1,":[77],"approaching":[78],"performance;":[80],"models":[82],"reach":[83],"about":[84],"70%":[85],"F1":[86],"in":[87,113],"Materials":[88],"Science.":[89],"results":[91],"highlight":[92],"strong":[93],"cross-lingual/cross-domain":[94],"transfer":[95],"Semantic-NMF-based":[97],"methods":[99],"demonstrate":[101],"scalable":[103],"path":[104],"mining":[107],"downstream":[109],"knowledge":[110],"graph":[111],"construction":[112],"under-represented":[114],"languages.":[115]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-31T00:00:00"}
