{"id":"https://openalex.org/W2137019100","doi":"https://doi.org/10.1145/1277741.1277917","title":"The influence of basic tokenization on biomedical document retrieval","display_name":"The influence of basic tokenization on biomedical document retrieval","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2137019100","doi":"https://doi.org/10.1145/1277741.1277917","mag":"2137019100"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5049879333","display_name":"Dolf Trieschnigg","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Dolf Trieschnigg","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049624750","display_name":"Wessel Kraaij","orcid":"https://orcid.org/0000-0001-7797-619X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wessel Kraaij","raw_affiliation_strings":["TNO ICT, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"TNO ICT, Delft, Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005474414","display_name":"Franciska de Jong","orcid":"https://orcid.org/0000-0003-1541-9712"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Franciska de Jong","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049879333"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":1.3089,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.79432199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9932000041007996,"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":0.983299970626831,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9615664482116699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7705135345458984},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6566251516342163},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.6013128161430359},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4753251373767853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4613059163093567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3425384759902954},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.08597642183303833}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9615664482116699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705135345458984},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6566251516342163},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.6013128161430359},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4753251373767853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4613059163093567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3425384759902954},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.08597642183303833},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/843dc37f-7b5c-4483-9410-36862eec47cb","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/843dc37f-7b5c-4483-9410-36862eec47cb","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Trieschnigg, R B, Kraaij, W & de Jong, F M G 2007, The Influence of Basic Tokenization on Biomedical Document Retrieval. in Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval., 10.1145/1277741.1277917, ACM Press, New York, NY, USA, pp. 803-804, 30th Annual International ACM/SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2007, Amsterdam, Netherlands, 23/07/07. https://doi.org/10.1145/1277741.1277917","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ris.utwente.nl:publications/843dc37f-7b5c-4483-9410-36862eec47cb","is_oa":false,"landing_page_url":"http://doi.acm.org/10.1145/1277741.1277917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328786","display_name":"Norwegian Biodiversity Information Centre","ror":"https://ror.org/04jnzhb65"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W108921306","https://openalex.org/W2039612385","https://openalex.org/W2103397879","https://openalex.org/W2114094147","https://openalex.org/W2126276057","https://openalex.org/W2132094268","https://openalex.org/W2791276966","https://openalex.org/W2917293077","https://openalex.org/W6678356393","https://openalex.org/W6679712908"],"related_works":["https://openalex.org/W2725310424","https://openalex.org/W4292346028","https://openalex.org/W4282591925","https://openalex.org/W4300598845","https://openalex.org/W2963023579","https://openalex.org/W2766198569","https://openalex.org/W2601638452","https://openalex.org/W4401641321","https://openalex.org/W2285263069","https://openalex.org/W4319309671"],"abstract_inverted_index":{"Tokenization":[0],"is":[1,13,44],"a":[2,62],"fundamental":[3],"preprocessing":[4],"step":[5],"in":[6,10,34,50,70],"Information":[7],"Retrieval":[8],"systems":[9],"which":[11],"text":[12],"turned":[14],"into":[15],"index":[16],"terms.":[17],"This":[18],"paper":[19],"quantifies":[20],"and":[21,38,64],"compares":[22],"the":[23,51,59,71],"influence":[24],"of":[25],"various":[26],"simple":[27],"tokenization":[28,52,55],"techniques":[29],"on":[30],"document":[31],"retrieval":[32,43],"effectiveness":[33],"two":[35],"domains:":[36],"biomedicine":[37],"news.":[39],"As":[40],"expected,":[41],"biomedical":[42,72],"more":[45],"sensitive":[46],"to":[47],"small":[48],"changes":[49],"method.":[53],"The":[54],"strategy":[56],"can":[57],"make":[58],"difference":[60],"between":[61],"mediocre":[63],"well":[65],"performing":[66],"IR":[67],"system,":[68],"especially":[69],"domain.":[73]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}