{"id":"https://openalex.org/W1512170015","doi":"https://doi.org/10.1186/1471-2105-7-334","title":"Machine learning and word sense disambiguation in the biomedical domain: design and evaluation issues","display_name":"Machine learning and word sense disambiguation in the biomedical domain: design and evaluation issues","publication_year":2006,"publication_date":"2006-07-05","ids":{"openalex":"https://openalex.org/W1512170015","doi":"https://doi.org/10.1186/1471-2105-7-334","mag":"1512170015","pmid":"https://pubmed.ncbi.nlm.nih.gov/16822321"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-334","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-334","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-334","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084072550","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-5274-4672"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Xu","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, 622 168th St, New York City, New York, USA. hua.xu@dbmi.columbia.edu","Department of Biomedical Informatics, Columbia University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, 622 168th St, New York City, New York, USA. hua.xu@dbmi.columbia.edu","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009202015","display_name":"Marianthi Markatou","orcid":"https://orcid.org/0000-0002-1453-8229"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marianthi Markatou","raw_affiliation_strings":["Department of Biostatistics, Columbia University, 722 168th St, New York City, New York, USA","Department of Biostatistics, Columbia University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Columbia University, 722 168th St, New York City, New York, USA","institution_ids":["https://openalex.org/I174216632"]},{"raw_affiliation_string":"Department of Biostatistics, Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030066738","display_name":"Rositsa B. Dimova","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]},{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rositsa Dimova","raw_affiliation_strings":["Department of Biostatistics, Columbia University, 722 168th St, New York City, New York, USA","Department of Biostatistics, Columbia University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Columbia University, 722 168th St, New York City, New York, USA","institution_ids":["https://openalex.org/I174216632"]},{"raw_affiliation_string":"Department of Biostatistics, Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]},{"id":"https://openalex.org/I2799903593","display_name":"Georgetown University Medical Center","ror":"https://ror.org/00hjz7x27","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799903593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University Medical Center, 4000 Reservoir Rd, Washington, DC, USA","Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University Medical Center, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University Medical Center, 4000 Reservoir Rd, Washington, DC, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]},{"raw_affiliation_string":"Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University Medical Center, Washington, USA","institution_ids":["https://openalex.org/I2799903593","https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109277899","display_name":"Carol Friedman","orcid":null},"institutions":[{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carol Friedman","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, 622 168th St, New York City, New York, USA","Department of Biomedical Informatics, Columbia University, New York City, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, 622 168th St, New York City, New York, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I174216632"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109277899"],"corresponding_institution_ids":["https://openalex.org/I174216632","https://openalex.org/I45029084","https://openalex.org/I78577930"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":2.1811,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.86124409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"1","first_page":"334","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.906000018119812,"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":0.906000018119812,"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":0.018300000578165054,"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/T10028","display_name":"Topic Modeling","score":0.012799999676644802,"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/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.7814242839813232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6400386095046997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5634490251541138},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5115460157394409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46316492557525635},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44759801030158997},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23604094982147217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07450568675994873}],"concepts":[{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.7814242839813232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6400386095046997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5634490251541138},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5115460157394409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46316492557525635},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44759801030158997},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23604094982147217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07450568675994873},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009716","descriptor_name":"Numerical Analysis, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-7-334","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-334","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-334","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16822321","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16822321","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8T43RJ8","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8T43RJ8","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articles"},{"id":"pmh:oai:doaj.org/article:a5577d7e5c4c4bf8a6e411416e83a673","is_oa":false,"landing_page_url":"https://doaj.org/article/a5577d7e5c4c4bf8a6e411416e83a673","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 7, Iss 1, p 334 (2006)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1550263","is_oa":true,"landing_page_url":"http://doi.org/10.1186/1471-2105-7-334","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"doi:10.7916/d8t43rj8","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8t43rj8","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-334","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-334","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-334","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G306318945","display_name":"Distances in Robust Model Selection","funder_award_id":"0504957","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6285711874","display_name":"SEI+II(BIO):     BioTagger - Biological Entity Tagging Using Online Resources and Machine Learning","funder_award_id":"0430743","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1512170015.pdf","grobid_xml":"https://content.openalex.org/works/W1512170015.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W116705248","https://openalex.org/W180865882","https://openalex.org/W1546317785","https://openalex.org/W1550258693","https://openalex.org/W1580481679","https://openalex.org/W1592053870","https://openalex.org/W1756650108","https://openalex.org/W1795234945","https://openalex.org/W1869958975","https://openalex.org/W1959755538","https://openalex.org/W1964922004","https://openalex.org/W1974758710","https://openalex.org/W1976252502","https://openalex.org/W1984293430","https://openalex.org/W2033200726","https://openalex.org/W2036255459","https://openalex.org/W2038585482","https://openalex.org/W2038728157","https://openalex.org/W2057867321","https://openalex.org/W2061327015","https://openalex.org/W2061396354","https://openalex.org/W2097058215","https://openalex.org/W2101171038","https://openalex.org/W2106564640","https://openalex.org/W2106894950","https://openalex.org/W2107580398","https://openalex.org/W2112865076","https://openalex.org/W2116040937","https://openalex.org/W2116972916","https://openalex.org/W2119412782","https://openalex.org/W2122763686","https://openalex.org/W2124617249","https://openalex.org/W2127112494","https://openalex.org/W2133864802","https://openalex.org/W2134769633","https://openalex.org/W2152016790","https://openalex.org/W2154250549","https://openalex.org/W2157025692","https://openalex.org/W2157870551","https://openalex.org/W2167277498","https://openalex.org/W2172000360","https://openalex.org/W2251794610","https://openalex.org/W2797114046","https://openalex.org/W3020747745","https://openalex.org/W4213060373","https://openalex.org/W4230797134","https://openalex.org/W4241727697","https://openalex.org/W4248219478","https://openalex.org/W4248234957","https://openalex.org/W4298186428"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2325435433","https://openalex.org/W2188275805","https://openalex.org/W2498383244","https://openalex.org/W2259621217","https://openalex.org/W2904069821","https://openalex.org/W2771050216","https://openalex.org/W3087778885","https://openalex.org/W1573688770","https://openalex.org/W2912005598"],"abstract_inverted_index":{"BACKGROUND:":[0],"Word":[1],"sense":[2,288,308],"disambiguation":[3],"(WSD)":[4],"is":[5,68,103,129,432],"critical":[6,433],"in":[7,82,232,267,274,421,449],"the":[8,13,55,66,83,92,108,113,124,135,151,159,164,167,171,179,182,185,188,195,241,246,260,263,287,298,312,321,331,385,402,425,438,441,447,450,453,465,468,471,481,495,498,501],"biomedical":[9,84,216],"domain":[10,85],"for":[11,58,371,409],"improving":[12],"precision":[14],"of":[15,61,98,112,153,158,166,170,176,181,187,190,197,227,230,309,320,333,384,416,427,446,467,494,500],"natural":[16],"language":[17],"processing":[18,63],"(NLP),":[19],"text":[20,62],"mining,":[21],"and":[22,44,86,101,110,122,137,174,221,335,443,452,475,484,497],"information":[23],"retrieval":[24],"systems":[25],"because":[26,115,226],"ambiguous":[27,172,192,215],"words":[28],"negatively":[29],"impact":[30,355],"accurate":[31],"access":[32],"to":[33,105,132,138,149,207,254,279,330,406,423,490],"literature":[34],"containing":[35,213],"biomolecular":[36],"entities,":[37],"such":[38],"as":[39,478,480],"genes,":[40],"proteins,":[41],"cells,":[42],"diseases,":[43],"other":[45,121],"important":[46],"entities.":[47],"Automated":[48],"techniques":[49,370],"have":[50,79,87,292],"been":[51,80],"developed":[52],"that":[53,354,375,400,420,434],"address":[54,134],"WSD":[56,74,198,313,469,472],"problem":[57,67],"a":[59,70,96,130,306,346,396],"number":[60,97],"situations,":[64],"but":[65,91,249],"still":[69],"challenging":[71],"one.":[72],"Supervised":[73],"machine":[75],"learning":[76],"(ML)":[77],"methods":[78,114,430,483],"applied":[81,206],"shown":[88],"promising":[89],"results,":[90],"results":[93,343,403,415],"typically":[94],"incorporate":[95],"confounding":[99],"factors,":[100],"it":[102,431],"problematic":[104],"truly":[106],"understand":[107,424],"effectiveness":[109],"generalizability":[111],"these":[116,428],"factors":[117,136],"interact":[118],"with":[119,411],"each":[120],"affect":[123,365],"final":[125],"results.":[126],"Thus,":[127],"there":[128,304,337],"need":[131],"explicitly":[133],"systematically":[139],"quantify":[140],"their":[141,233],"effects":[142],"on":[143,194,295,437],"performance.":[144],"RESULTS:":[145],"Experiments":[146],"were":[147,205,224,265,300,328],"designed":[148],"measure":[150,180],"effect":[152,294],"\"sample":[154],"size\"":[155],"(i.e.":[156,163,178,257],"size":[157,243,276,445],"datasets),":[160],"\"sense":[161],"distribution\"":[162],"distribution":[165,289,442],"different":[168,362],"meanings":[169,186],"word)":[173,193],"\"degree":[175],"difficulty\"":[177],"distances":[183,261],"between":[184,262,342],"senses":[189,256,264,299,448],"an":[191,208,270,293,491],"performance":[196,281,296,356,366,426],"classifiers.":[199],"Support":[200],"Vector":[201],"Machine":[202],"(SVM)":[203],"classifiers":[204],"automatically":[209],"generated":[210],"data":[211],"set":[212],"four":[214,392],"abbreviations:":[217],"BPD,":[218],"BSA,":[219],"PCA,":[220],"RSV,":[222],"which":[223,283],"chosen":[225],"varying":[228],"degrees":[229],"differences":[231],"respective":[234],"senses.":[235],"Results":[236],"showed":[237],"that:":[238],"1)":[239],"increasing":[240],"sample":[242,275,444],"generally":[244],"reduced":[245],"error":[247,326],"rate,":[248],"this":[250],"was":[251,277,284,305,315,338],"limited":[252],"mainly":[253],"well-separated":[255],"cases":[258,269],"where":[259],"large);":[266],"difficult":[268],"unusually":[271],"large":[272],"increase":[273,280],"needed":[278],"slightly,":[282],"impractical,":[285],"2)":[286],"did":[290],"not":[291,316,476],"when":[297,303,344,367],"separable,":[301],"3)":[302],"majority":[307,323],"over":[310],"90%,":[311],"classifier":[314],"better":[317],"than":[318],"use":[319],"simple":[322],"sense,":[324],"4)":[325],"rates":[327],"proportional":[329],"similarity":[332],"senses,":[334],"5)":[336],"no":[339],"statistical":[340,398],"difference":[341],"using":[345,368],"5-fold":[347],"or":[348,456],"10-fold":[349],"cross-validation":[350],"method.":[351],"Other":[352],"issues":[353],"are":[357,404],"also":[358,463],"enumerated.":[359],"CONCLUSION:":[360],"Several":[361],"independent":[363],"aspects":[364],"ML":[369,429,482],"WSD.":[372],"We":[373],"found":[374],"combining":[376],"them":[377],"into":[378],"one":[379],"single":[380],"result":[381],"obscures":[382],"understanding":[383,493],"underlying":[386],"methods.":[387],"Although":[388],"we":[389,394],"studied":[390],"only":[391],"abbreviations,":[393],"utilized":[395],"well-established":[397],"method":[399],"guarantees":[401],"likely":[405],"be":[407],"generalizable":[408],"abbreviations":[410],"similar":[412],"characteristics.":[413],"The":[414],"our":[417],"experiments":[418],"show":[419],"order":[422],"papers":[435,461],"report":[436],"baseline":[439],"performance,":[440],"datasets,":[451],"standard":[454],"deviation":[455],"confidence":[457],"intervals.":[458],"In":[459],"addition,":[460],"should":[462,488],"characterize":[464],"difficulty":[466],"task,":[470],"situations":[473],"addressed":[474],"addressed,":[477],"well":[479],"features":[485],"used.":[486],"This":[487],"lead":[489],"improved":[492],"generalizablility":[496],"limitations":[499],"methodology.":[502]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}