{"id":"https://openalex.org/W2127776561","doi":"https://doi.org/10.3115/1220175.1220274","title":"You can't beat frequency (unless you use linguistic knowledge)","display_name":"You can't beat frequency (unless you use linguistic knowledge)","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2127776561","doi":"https://doi.org/10.3115/1220175.1220274","mag":"2127776561"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220274","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220274","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086045687","display_name":"Joachim Wermter","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joachim Wermter","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Jena, Germany","Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Jena, Germany","institution_ids":[]},{"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 & Information Engineering (JULIE) Lab, Jena, Germany","Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany"],"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Jena, Germany","institution_ids":[]},{"raw_affiliation_string":"Jena University Language and Information Engineering (JULIE) Lab, Jena, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086045687"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0664,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.9378161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"785","last_page":"792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9959999918937683,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9959999918937683,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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":0.9775999784469604,"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/terminology","display_name":"Terminology","score":0.7705700397491455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5693530440330505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5291963815689087},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5027036666870117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4329929053783417},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.43185046315193176},{"id":"https://openalex.org/keywords/significant-difference","display_name":"Significant difference","score":0.426474392414093},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35301142930984497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29957306385040283}],"concepts":[{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.7705700397491455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5693530440330505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5291963815689087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5027036666870117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4329929053783417},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43185046315193176},{"id":"https://openalex.org/C3018023364","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Significant difference","level":2,"score":0.426474392414093},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35301142930984497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29957306385040283},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1220175.1220274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220274","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220274","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220274","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2127776561.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1966475681","https://openalex.org/W2049107599","https://openalex.org/W2050034861","https://openalex.org/W2065326249","https://openalex.org/W2103464847","https://openalex.org/W2158348268","https://openalex.org/W2166776180","https://openalex.org/W2314731117","https://openalex.org/W2439228446","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2374093222","https://openalex.org/W3164630567"],"abstract_inverted_index":{"In":[0],"the":[1],"past":[2],"years,":[3],"a":[4,82],"number":[5],"of":[6,25,43,54,71],"lexical":[7],"association":[8],"measures":[9,33,63],"have":[10],"been":[11],"studied":[12],"to":[13],"help":[14],"extract":[15],"new":[16],"scientific":[17],"terminology":[18],"or":[19],"general-language":[20],"collocations.":[21],"The":[22],"implicit":[23],"assumption":[24],"this":[26,50],"research":[27],"was":[28],"that":[29,60],"newly":[30],"designed":[31],"term":[32],"involving":[34],"more":[35,76],"sophisticated":[36],"statistical":[37],"criteria":[38],"would":[39],"outperform":[40],"simple":[41],"counts":[42],"co-occurrence":[44],"frequencies.":[45],"We":[46],"here":[47],"explicitly":[48],"test":[49],"assumption.":[51],"By":[52],"way":[53],"four":[55],"qualitative":[56],"criteria,":[57],"we":[58],"show":[59],"purely":[61],"statistics-based":[62],"reveal":[64,80],"virtually":[65],"no":[66],"difference":[67],"compared":[68],"with":[69],"frequency":[70],"occurrence":[72],"counts,":[73],"while":[74],"linguistically":[75],"informed":[77],"metrics":[78],"do":[79],"such":[81],"marked":[83],"difference.":[84]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}