{"id":"https://openalex.org/W2434774946","doi":"https://doi.org/10.1145/1088622.1088661","title":"Extracting significant words from corpora for ontology extraction","display_name":"Extracting significant words from corpora for ontology extraction","publication_year":2005,"publication_date":"2005-10-02","ids":{"openalex":"https://openalex.org/W2434774946","doi":"https://doi.org/10.1145/1088622.1088661","mag":"2434774946"},"language":"en","primary_location":{"id":"doi:10.1145/1088622.1088661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088661","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/A5041664344","display_name":"Dileep G. Damle","orcid":null},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dileep Damle","raw_affiliation_strings":["The Open University, Milton Keynes, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Open University, Milton Keynes, UK","institution_ids":["https://openalex.org/I204136569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037549599","display_name":"Victoria Uren","orcid":"https://orcid.org/0000-0002-1303-5574"},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victoria Uren","raw_affiliation_strings":["The Open University, Milton Keynes, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Open University, Milton Keynes, UK","institution_ids":["https://openalex.org/I204136569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204136569"],"apc_list":null,"apc_paid":null,"fwci":1.7332,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86295125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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":0.9990000128746033,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9988999962806702,"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":0.7996364235877991},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7669718265533447},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7351392507553101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.660677969455719},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6432509422302246},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6006187200546265},{"id":"https://openalex.org/keywords/ontology-learning","display_name":"Ontology learning","score":0.5754561424255371},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5515904426574707},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5381141304969788},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5100803971290588},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32926154136657715},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.22770807147026062},{"id":"https://openalex.org/keywords/upper-ontology","display_name":"Upper ontology","score":0.22240608930587769},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10579130053520203},{"id":"https://openalex.org/keywords/suggested-upper-merged-ontology","display_name":"Suggested Upper Merged Ontology","score":0.10339346528053284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996364235877991},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7669718265533447},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7351392507553101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660677969455719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6432509422302246},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6006187200546265},{"id":"https://openalex.org/C2777002027","wikidata":"https://www.wikidata.org/wiki/Q3620938","display_name":"Ontology learning","level":5,"score":0.5754561424255371},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5515904426574707},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5381141304969788},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5100803971290588},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32926154136657715},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.22770807147026062},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.22240608930587769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10579130053520203},{"id":"https://openalex.org/C50971890","wikidata":"https://www.wikidata.org/wiki/Q7635093","display_name":"Suggested Upper Merged Ontology","level":4,"score":0.10339346528053284},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1088622.1088661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1088622.1088661","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.489","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aktors.org/akt/events/docsympjune2005/proceedings/damle-corpora-ontology-extraction.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1486212465","https://openalex.org/W1489181569","https://openalex.org/W1975690018","https://openalex.org/W1990438144","https://openalex.org/W2056189598","https://openalex.org/W2080579867","https://openalex.org/W2091273188","https://openalex.org/W2104447546","https://openalex.org/W2112652344","https://openalex.org/W2113110240","https://openalex.org/W2116411927","https://openalex.org/W2116780029","https://openalex.org/W2132232128","https://openalex.org/W2154384676","https://openalex.org/W2407557870","https://openalex.org/W2914605928","https://openalex.org/W4293690910"],"related_works":["https://openalex.org/W1771592750","https://openalex.org/W2024342824","https://openalex.org/W4255991504","https://openalex.org/W169590660","https://openalex.org/W111088122","https://openalex.org/W1576659514","https://openalex.org/W2138657316","https://openalex.org/W2502600090","https://openalex.org/W2227378261","https://openalex.org/W4240164716"],"abstract_inverted_index":{"We":[0,32],"show":[1],"a":[2,9],"new":[3],"method":[4],"for":[5,17],"term":[6],"extraction":[7],"from":[8],"domain":[10],"relevant":[11],"corpus":[12],"using":[13],"natural":[14],"language":[15],"processing":[16],"the":[18,35,43,53,58],"purposes":[19],"of":[20,37,45],"semi-automatic":[21],"ontology":[22],"learning.":[23],"Literature":[24],"shows":[25],"that":[26,34],"topical":[27],"words":[28,62],"occur":[29],"in":[30,61],"bursts.":[31],"find":[33],"ranking":[36],"extracted":[38],"terms":[39],"is":[40],"insensitive":[41],"to":[42,52],"choice":[44],"population":[46],"model,":[47],"but":[48],"calculating":[49],"frequencies":[50],"relative":[51],"burst":[54],"size":[55],"rather":[56],"than":[57],"document":[59],"length":[60],"yields":[63],"significantly":[64],"different":[65],"results.":[66]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}