{"id":"https://openalex.org/W3212619479","doi":"https://doi.org/10.1021/acs.jcim.1c00554","title":"Machine-Guided Polymer Knowledge Extraction Using Natural Language Processing: The Example of Named Entity Normalization","display_name":"Machine-Guided Polymer Knowledge Extraction Using Natural Language Processing: The Example of Named Entity Normalization","publication_year":2021,"publication_date":"2021-11-09","ids":{"openalex":"https://openalex.org/W3212619479","doi":"https://doi.org/10.1021/acs.jcim.1c00554","mag":"3212619479","pmid":"https://pubmed.ncbi.nlm.nih.gov/34752101"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00554","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00554","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5014921627","display_name":"Pranav Shetty","orcid":"https://orcid.org/0000-0003-2015-9556"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranav Shetty","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta, Georgia 30332, United States"],"raw_orcid":"https://orcid.org/0000-0003-2015-9556","affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta, Georgia 30332, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031952600","display_name":"Rampi Ramprasad","orcid":"https://orcid.org/0000-0003-4630-1565"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rampi Ramprasad","raw_affiliation_strings":["School of Materials Science and Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta, Georgia 30332, United States"],"raw_orcid":"https://orcid.org/0000-0003-4630-1565","affiliations":[{"raw_affiliation_string":"School of Materials Science and Engineering, Georgia Institute of Technology, 771 Ferst Drive NW, Atlanta, Georgia 30332, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031952600"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.2822,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.78485189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"61","issue":"11","first_page":"5377","last_page":"5385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.7658456563949585},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7335448861122131},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6644384860992432},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6225252151489258},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5727407336235046},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.565293550491333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5545639991760254},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.511604368686676},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45766618847846985},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3709227442741394},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.2027074098587036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08673915266990662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658456563949585},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7335448861122131},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6644384860992432},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6225252151489258},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5727407336235046},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.565293550491333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5545639991760254},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.511604368686676},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45766618847846985},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3709227442741394},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2027074098587036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08673915266990662},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011108","descriptor_name":"Polymers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c00554","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00554","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:34752101","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34752101","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8799999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1698051709","display_name":null,"funder_award_id":"N00014-19-1-2103","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3942647001","display_name":null,"funder_award_id":"N00014-20-1-2175","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1582827147","https://openalex.org/W1991449795","https://openalex.org/W1996118086","https://openalex.org/W2011857854","https://openalex.org/W2015809202","https://openalex.org/W2060765209","https://openalex.org/W2092368765","https://openalex.org/W2139956879","https://openalex.org/W2143434140","https://openalex.org/W2144735217","https://openalex.org/W2149029960","https://openalex.org/W2153233077","https://openalex.org/W2153839667","https://openalex.org/W2169491861","https://openalex.org/W2170531092","https://openalex.org/W2177317049","https://openalex.org/W2187089797","https://openalex.org/W2493916176","https://openalex.org/W2523785361","https://openalex.org/W2761714433","https://openalex.org/W2766362701","https://openalex.org/W2769041395","https://openalex.org/W2780553247","https://openalex.org/W2948909602","https://openalex.org/W2950627632","https://openalex.org/W2950694993","https://openalex.org/W2953641512","https://openalex.org/W2959716049","https://openalex.org/W2964164050","https://openalex.org/W2964300937","https://openalex.org/W2964864162","https://openalex.org/W2980932864","https://openalex.org/W2995854597","https://openalex.org/W2999645992","https://openalex.org/W3008388458","https://openalex.org/W3010639504","https://openalex.org/W3015467311","https://openalex.org/W3032308670","https://openalex.org/W3034055367","https://openalex.org/W3095028680","https://openalex.org/W3096386116","https://openalex.org/W3100445615","https://openalex.org/W3112850967","https://openalex.org/W3114168740","https://openalex.org/W3135847490","https://openalex.org/W3175827219","https://openalex.org/W3196212666"],"related_works":["https://openalex.org/W4205454697","https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W2621151902","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2793132289","https://openalex.org/W2520117834","https://openalex.org/W626980589"],"abstract_inverted_index":{"A":[0],"rich":[1],"body":[2],"of":[3,14,36,64,72,79,132,148,155,171,190,203,233],"literature":[4],"has":[5,29],"emerged":[6],"in":[7,55,86,105,123,178,221],"recent":[8],"years":[9],"that":[10,39,42,74,109,174],"discusses":[11],"the":[12,34,52,62,83,89,114,120,124,130,167,179,210,228,236],"extraction":[13,232],"structured":[15],"information":[16],"from":[17,187,235],"materials":[18,73],"science":[19],"text":[20],"through":[21],"named":[22,66,110,184],"entity":[23,54],"recognition":[24],"models.":[25],"Relatively":[26],"little":[27],"work":[28,107,214],"been":[30],"done":[31],"to":[32,51,88,113,137,160,165,208],"address":[33,61],"\"normalization\"":[35],"extracted":[37,186],"entities,":[38,67,143],"is,":[40],"recognizing":[41],"two":[43],"or":[44],"more":[45],"seemingly":[46],"different":[47],"entities":[48,111,185],"actually":[49],"refer":[50],"same":[53,84,115,121],"reality.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,194],"normalization":[63,211],"polymer":[65,116,156,183,237],"polymers":[68,173],"being":[69],"a":[70,77,151,218,222],"class":[71],"often":[75],"have":[76,93],"variety":[78],"common":[80],"names":[81,157],"for":[82,227],"material":[85],"addition":[87],"IUPAC":[90],"name.":[91],"We":[92,128],"trained":[94],"supervised":[95],"clustering":[96],"models":[97],"using":[98],"Word2Vec":[99],"and":[100,139,164,230],"fastText":[101],"word":[102,125],"embeddings":[103],"reported":[104,177],"previous":[106],"so":[108],"referring":[112],"are":[117,175],"categorized":[118],"within":[119],"cluster":[122,138],"embedding":[126],"space.":[127],"report":[129],"use":[131],"parameterized":[133],"cosine":[134],"distance":[135],"functions":[136],"normalize":[140],"textually":[141],"derived":[142],"achieving":[144],"an":[145],"F1":[146],"score":[147],"0.85.":[149],"Furthermore,":[150],"labeled":[152],"data":[153],"set":[154],"was":[158],"utilized":[159],"train":[161,209],"our":[162,188],"model":[163],"infer":[166],"true":[168],"total":[169],"number":[170],"unique":[172,197,200],"actively":[176],"literature.":[180,238],"For":[181],"\u223c15,500":[182],"corpus":[189],"0.5":[191],"million":[192],"papers,":[193],"detected":[195],"6734":[196],"clusters":[198],"(i.e.,":[199],"polymers),":[201],"632":[202],"which":[204],"were":[205],"manually":[206],"curated":[207],"model.":[212],"This":[213],"will":[215],"serve":[216],"as":[217],"critical":[219],"ingredient":[220],"natural":[223],"language":[224],"processing-based":[225],"pipeline":[226],"automatic":[229],"efficient":[231],"knowledge":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}