{"id":"https://openalex.org/W4388452573","doi":"https://doi.org/10.1021/acs.jcim.3c01281","title":"Snowball 2.0: Generic Material Data Parser for ChemDataExtractor","display_name":"Snowball 2.0: Generic Material Data Parser for ChemDataExtractor","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388452573","doi":"https://doi.org/10.1021/acs.jcim.3c01281","pmid":"https://pubmed.ncbi.nlm.nih.gov/37934697"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c01281","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c01281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021467511","display_name":"Qingyang Dong","orcid":"https://orcid.org/0000-0002-8782-7638"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Qingyang Dong","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8782-7638","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068607578","display_name":"Jacqueline M. Cole","orcid":"https://orcid.org/0000-0002-1552-8743"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Jacqueline M. Cole","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1552-8743","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]},{"raw_affiliation_string":"ISIS Neutron and Muon Source, STFC Rutherford Appleton Laboratory, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0QX, U.K","institution_ids":["https://openalex.org/I1286704778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068607578"],"corresponding_institution_ids":["https://openalex.org/I1286704778","https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":0.4237,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53098746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"63","issue":"22","first_page":"7045","last_page":"7055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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":0.9998999834060669,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9496999979019165,"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/parsing","display_name":"Parsing","score":0.8256122469902039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7847012877464294},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7392380237579346},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6181793808937073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5706762075424194},{"id":"https://openalex.org/keywords/snowball-sampling","display_name":"Snowball sampling","score":0.5619614720344543},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5428909659385681},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5403931140899658},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5313513875007629},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4991128444671631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4861859679222107},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4214492738246918},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.41969045996665955},{"id":"https://openalex.org/keywords/snowball-earth","display_name":"Snowball Earth","score":0.41704681515693665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3754436671733856},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11289846897125244}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8256122469902039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847012877464294},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7392380237579346},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6181793808937073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706762075424194},{"id":"https://openalex.org/C106399304","wikidata":"https://www.wikidata.org/wiki/Q868123","display_name":"Snowball sampling","level":2,"score":0.5619614720344543},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5428909659385681},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5403931140899658},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5313513875007629},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4991128444671631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4861859679222107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4214492738246918},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41969045996665955},{"id":"https://openalex.org/C168816792","wikidata":"https://www.wikidata.org/wiki/Q214689","display_name":"Snowball Earth","level":3,"score":0.41704681515693665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3754436671733856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11289846897125244},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C15739521","wikidata":"https://www.wikidata.org/wiki/Q602963","display_name":"Glacial period","level":2,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c01281","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37934697","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37934697","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},{"id":"pmh:oai:pubmedcentral.nih.gov:10685441","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10685441","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10685441/pdf/ci3c01281.pdf","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":"J Chem Inf Model","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/361755","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/361755","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/59dcbb7b-f598-4885-8019-e1377a568981/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"},{"id":"pmh:oai:purl.org/net/epubs:work/56345892","is_oa":true,"landing_page_url":"https://epubs.stfc.ac.uk/work/56345892","pdf_url":null,"source":{"id":"https://openalex.org/S4306400334","display_name":"Science and Technology Facilities Council","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c01281","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01281","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c01281","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1531024995","display_name":null,"funder_award_id":"RCSRF1819\\7\\10","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"}],"funders":[{"id":"https://openalex.org/F4320307790","display_name":"BASF","ror":"https://ror.org/01q8f6705"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"},{"id":"https://openalex.org/F4320338254","display_name":"ISIS Neutron and Muon Source","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388452573.pdf","grobid_xml":"https://content.openalex.org/works/W4388452573.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W617139115","https://openalex.org/W1985697096","https://openalex.org/W1992985800","https://openalex.org/W1997841190","https://openalex.org/W2111044246","https://openalex.org/W2117363206","https://openalex.org/W2134329894","https://openalex.org/W2136794542","https://openalex.org/W2161344493","https://openalex.org/W2165671627","https://openalex.org/W2523785361","https://openalex.org/W2755202310","https://openalex.org/W2766362701","https://openalex.org/W2808304511","https://openalex.org/W2992302948","https://openalex.org/W3006937107","https://openalex.org/W3047398431","https://openalex.org/W3118795178","https://openalex.org/W3200122731","https://openalex.org/W4214535912","https://openalex.org/W4225378608","https://openalex.org/W4225409008","https://openalex.org/W4281617541","https://openalex.org/W4283074682","https://openalex.org/W4307139584"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2004087619","https://openalex.org/W2469016277","https://openalex.org/W2757101400","https://openalex.org/W1982302668","https://openalex.org/W2362196274","https://openalex.org/W2557094866","https://openalex.org/W1990527953","https://openalex.org/W2240384024","https://openalex.org/W2766839647"],"abstract_inverted_index":{"High":[0],"Resolution":[1],"Image":[2],"Download":[3],"MS":[4],"PowerPoint":[5],"Slide":[6],"The":[7,27],"ever-growing":[8],"amount":[9],"of":[10,23,47,110,129,179],"chemical":[11,36,89],"data":[12,54,181],"found":[13],"in":[14,30,136,158,176],"the":[15,21,31,45,143,177],"scientific":[16],"literature":[17],"has":[18,41,147],"led":[19],"to":[20,33,86],"emergence":[22],"data-driven":[24],"materials":[25],"discovery.":[26],"first":[28],"step":[29],"pipeline,":[32],"automatically":[34],"extract":[35,87],"information":[37,114],"from":[38,116],"plain":[39],"text,":[40],"been":[42,148],"driven":[43],"by":[44,102],"development":[46],"software":[48],"toolkits":[49],"such":[50],"as":[51],"ChemDataExtractor.":[52],"Such":[53],"extraction":[55],"processes":[56],"have":[57],"created":[58],"a":[59,73,78,106,133],"demand":[60],"for":[61,169],"parsers":[62],"that":[63],"efficiently":[64],"enable":[65],"text":[66],"mining.":[67],"Here,":[68],"we":[69],"present":[70],"Snowball":[71,119,126,130,154,161,183],"2.0,":[72,152],"sentence":[74],"parser":[75],"based":[76],"on":[77,122],"semisupervised":[79],"machine-learning":[80],"algorithm.":[81],"It":[82],"can":[83],"be":[84],"used":[85],"any":[88],"property":[90],"without":[91],"additional":[92],"training.":[93],"We":[94],"validate":[95],"its":[96],"precision,":[97],"recall,":[98],"and":[99,104,165,171,192],"F":[100],"-score":[101],"training":[103],"testing":[105],"model":[107],"with":[108,138],"sentences":[109],"semiconductor":[111],"band":[112],"gap":[113],"curated":[115],"journal":[117],"articles.":[118],"2.0":[120,131,155,162,184],"builds":[121],"two":[123],"previously":[124],"developed":[125],"algorithms.":[127],"Evaluation":[128],"shows":[132],"15\u201320%":[134],"increase":[135],"recall":[137],"marginally":[139],"reduced":[140],"precision":[141],"over":[142],"previous":[144],"version":[145],"which":[146],"incorporated":[149],"into":[150],"ChemDataExtractor":[151],"giving":[153],"better":[156,166,187],"performance":[157],"most":[159],"configurations.":[160],"offers":[163],"more":[164,174],"parsing":[167],"options":[168],"ChemDataExtractor,":[170],"it":[172],"is":[173],"capable":[175],"pipeline":[178],"automated":[180],"extraction.":[182],"also":[185],"features":[186],"generalizability,":[188],"performance,":[189],"learning":[190],"efficiencies,":[191],"user-friendliness.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}