{"id":"https://openalex.org/W2029153635","doi":"https://doi.org/10.1145/1088622.1088648","title":"Finding new terminology in very large corpora","display_name":"Finding new terminology in very large corpora","publication_year":2005,"publication_date":"2005-10-02","ids":{"openalex":"https://openalex.org/W2029153635","doi":"https://doi.org/10.1145/1088622.1088648","mag":"2029153635"},"language":"en","primary_location":{"id":"doi:10.1145/1088622.1088648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international conference on Knowledge capture","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086045687","display_name":"Joachim Wermter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joachim Wermter","raw_affiliation_strings":["Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044841280","display_name":"Udo Hahn","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Udo Hahn","raw_affiliation_strings":["Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1438,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94862901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T12881","display_name":"linguistics and terminology studies","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.8239953517913818},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.8134761452674866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641655206680298},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.7537734508514404},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.69254469871521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.626767098903656},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.614609956741333},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5463131666183472},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46974900364875793},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4502623677253723},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.435558944940567},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4176207482814789},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3098565936088562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14891678094863892}],"concepts":[{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.8239953517913818},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.8134761452674866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641655206680298},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7537734508514404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.69254469871521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626767098903656},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.614609956741333},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5463131666183472},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46974900364875793},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4502623677253723},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.435558944940567},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4176207482814789},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3098565936088562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14891678094863892},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1088622.1088648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international conference on Knowledge capture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W27076413","https://openalex.org/W78496535","https://openalex.org/W102264027","https://openalex.org/W306272353","https://openalex.org/W1574901103","https://openalex.org/W1957641795","https://openalex.org/W1966475681","https://openalex.org/W1967488025","https://openalex.org/W1988995507","https://openalex.org/W2006624771","https://openalex.org/W2039612385","https://openalex.org/W2044070623","https://openalex.org/W2049107599","https://openalex.org/W2050034861","https://openalex.org/W2103464847","https://openalex.org/W2145734530","https://openalex.org/W2158102230","https://openalex.org/W2314731117","https://openalex.org/W4243819499","https://openalex.org/W4245051455","https://openalex.org/W4246066782"],"related_works":["https://openalex.org/W2011383762","https://openalex.org/W4327499987","https://openalex.org/W2048414027","https://openalex.org/W3173084154","https://openalex.org/W2940857995","https://openalex.org/W2895883758","https://openalex.org/W2940684586","https://openalex.org/W2809276897","https://openalex.org/W2031891814","https://openalex.org/W353876725"],"abstract_inverted_index":{"Most":[0],"technical":[1,19],"and":[2,70,85,137],"scientific":[3,21],"terms":[4,40,60],"are":[5,18],"comprised":[6],"of":[7,25,46,59,127],"complex,":[8],"multi-word":[9],"noun":[10,16,31,51,72],"phrases":[11,17,32,73],"but":[12],"certainly":[13],"not":[14],"all":[15],"or":[20],"terms.":[22],"The":[23],"distinction":[24],"specific":[26],"terminology":[27,89,116],"from":[28,75],"common":[29],"non-specific":[30,50],"can":[33],"be":[34],"based":[35],"on":[36,67],"the":[37,55,64,125],"observation":[38],"that":[39,97,124],"reveal":[41],"a":[42,76,110,131],"much":[43],"lesser":[44],"degree":[45],"distributional":[47],"variation":[48],"than":[49],"phrases.":[52],"We":[53,119],"formalize":[54],"limited":[56],"paradigmatic":[57],"modifiability":[58],"and,":[61,106],"subsequently,":[62],"test":[63],"corresponding":[65],"algorithm":[66,99],"bigram,":[68],"trigram":[69],"quadgram":[71],"extracted":[74],"104-million-word":[77],"biomedical":[78,88],"text":[79],"corpus.":[80],"Using":[81],"an":[82,91],"already":[83],"existing":[84],"community-wide":[86],"curated":[87],"as":[90,109],"evaluation":[92],"gold":[93],"standard,":[94],"we":[95],"show":[96],"our":[98,128],"significantly":[100],"outperforms":[101],"standard":[102],"term":[103],"identification":[104,117],"measures":[105],"therefore,":[107],"qualifies":[108],"high-performant":[111],"building":[112],"block":[113],"for":[114],"any":[115],"system.":[118],"also":[120],"provide":[121],"empirical":[122],"evidence":[123],"superiority":[126],"approach,":[129],"beyond":[130],"10-million-word":[132],"threshold,":[133],"is":[134],"essentially":[135],"domain-":[136],"corpus-size-independent.":[138]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}