{"id":"https://openalex.org/W4393277170","doi":"https://doi.org/10.1021/acs.jcim.4c00063","title":"How Beneficial Is Pretraining on a Narrow Domain-Specific Corpus for Information Extraction about Photocatalytic Water Splitting?","display_name":"How Beneficial Is Pretraining on a Narrow Domain-Specific Corpus for Information Extraction about Photocatalytic Water Splitting?","publication_year":2024,"publication_date":"2024-03-28","ids":{"openalex":"https://openalex.org/W4393277170","doi":"https://doi.org/10.1021/acs.jcim.4c00063","pmid":"https://pubmed.ncbi.nlm.nih.gov/38544337"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00063","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00063","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00063","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.4c00063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084387381","display_name":"Taketomo Isazawa","orcid":"https://orcid.org/0000-0003-0475-403X"},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Taketomo Isazawa","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0475-403X","affiliations":[{"raw_affiliation_string":"Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"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"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jacqueline M. Cole","raw_affiliation_strings":["Cavendish Laboratory, Department of Physics, University of Cambridge, J. J. Thomson Avenue, 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, J. J. Thomson Avenue, Cambridge CB3 0HE, U.K","institution_ids":["https://openalex.org/I241749"]},{"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":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068607578"],"corresponding_institution_ids":["https://openalex.org/I1286704778","https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":2.2245,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88923245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"64","issue":"8","first_page":"3205","last_page":"3212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9902999997138977,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9769999980926514,"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/task","display_name":"Task (project management)","score":0.6977599859237671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973088383674622},{"id":"https://openalex.org/keywords/photocatalysis","display_name":"Photocatalysis","score":0.6570782661437988},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6311723589897156},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5943986177444458},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5457351803779602},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5217303037643433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4994652271270752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45324742794036865},{"id":"https://openalex.org/keywords/water-extraction","display_name":"Water extraction","score":0.44574087858200073},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4340885281562805},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.42075392603874207},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.21445918083190918},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.19787928462028503},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11069780588150024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09535759687423706}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6977599859237671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973088383674622},{"id":"https://openalex.org/C65165184","wikidata":"https://www.wikidata.org/wiki/Q218831","display_name":"Photocatalysis","level":3,"score":0.6570782661437988},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6311723589897156},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5943986177444458},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5457351803779602},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5217303037643433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4994652271270752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45324742794036865},{"id":"https://openalex.org/C2778395939","wikidata":"https://www.wikidata.org/wiki/Q2160967","display_name":"Water extraction","level":3,"score":0.44574087858200073},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4340885281562805},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.42075392603874207},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21445918083190918},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.19787928462028503},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11069780588150024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09535759687423706},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C161790260","wikidata":"https://www.wikidata.org/wiki/Q82264","display_name":"Catalysis","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D002384","descriptor_name":"Catalysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002384","descriptor_name":"Catalysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002384","descriptor_name":"Catalysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002384","descriptor_name":"Catalysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002384","descriptor_name":"Catalysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002384","descriptor_name":"Catalysis","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":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014867","descriptor_name":"Water","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055668","descriptor_name":"Photochemical Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":7,"locations":[{"id":"doi:10.1021/acs.jcim.4c00063","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00063","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00063","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:38544337","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38544337","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:osti.gov:2469488","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2469488","pdf_url":"https://www.osti.gov/servlets/purl/2469488","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11040717","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11040717","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11040717/pdf/ci4c00063.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:1810/367495","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/367495","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/c56bf75b-e1e6-4ab4-af91-6e443fefd2ba/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:www.repository.cam.ac.uk:1810/368997","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/368997","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/9115b2ed-5dd8-4070-b92e-a06c35a37f76/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/57839432","is_oa":true,"landing_page_url":"https://epubs.stfc.ac.uk/work/57839432","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.4c00063","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00063","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.4c00063","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/6","display_name":"Clean water and sanitation","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3075337988","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G4173398021","display_name":null,"funder_award_id":"RCSRF1819/7/10","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5085543421","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"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/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393277170.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1993068932","https://openalex.org/W2523785361","https://openalex.org/W2911489562","https://openalex.org/W2949922292","https://openalex.org/W2963323070","https://openalex.org/W2963809228","https://openalex.org/W2979826702","https://openalex.org/W3015453090","https://openalex.org/W3047398431","https://openalex.org/W3129831491","https://openalex.org/W3200122731","https://openalex.org/W3201869313","https://openalex.org/W4229443452","https://openalex.org/W4296836559","https://openalex.org/W4301409532","https://openalex.org/W4327913228","https://openalex.org/W4386955948","https://openalex.org/W4391836235","https://openalex.org/W4392002118"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2386929875","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668"],"abstract_inverted_index":{"Language":[0],"models":[1,38],"trained":[2,39],"on":[3,23,40,66,76,79],"domain-specific":[4],"corpora":[5,43,62],"have":[6],"been":[7,21],"employed":[8],"to":[9],"increase":[10],"the":[11,48,91,95],"performance":[12,65,85],"in":[13,47,89],"specialized":[14],"tasks.":[15,68],"However,":[16],"little":[17],"previous":[18,87],"work":[19,88],"has":[20],"reported":[22],"how":[24],"specific":[25,42,61],"a":[26,34,71,103,108],"\"domain-specific\"":[27],"corpus":[28],"should":[29],"be.":[30],"Here,":[31],"we":[32],"test":[33],"number":[35],"of":[36,50,105,110],"language":[37],"varyingly":[41],"by":[44],"employing":[45],"them":[46],"task":[49],"extracting":[51],"information":[52,100],"from":[53,74],"photocatalytic":[54,80,97],"water":[55,81],"splitting.":[56],"We":[57],"find":[58],"that":[59],"more":[60],"can":[63],"benefit":[64],"downstream":[67],"Furthermore,":[69],"PhotocatalysisBERT,":[70],"pretrained":[72],"model":[73],"scratch":[75],"scientific":[77],"papers":[78],"splitting,":[82],"demonstrates":[83],"improved":[84],"over":[86],"associating":[90],"correct":[92,96],"photocatalyst":[93],"with":[94],"activity":[98],"during":[99],"extraction,":[101],"achieving":[102],"precision":[104],"60.8(+11.5)%":[106],"and":[107],"recall":[109],"37.2(+4.5)%.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}
