{"id":"https://openalex.org/W2974767492","doi":"https://doi.org/10.1145/3342558.3345411","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","display_name":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","publication_year":2019,"publication_date":"2019-09-19","ids":{"openalex":"https://openalex.org/W2974767492","doi":"https://doi.org/10.1145/3342558.3345411","mag":"2974767492"},"language":"en","primary_location":{"id":"doi:10.1145/3342558.3345411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-02294424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077452892","display_name":"Luca Foppiano","orcid":"https://orcid.org/0000-0002-6114-6164"},"institutions":[{"id":"https://openalex.org/I205401836","display_name":"National Institute for Materials Science","ror":"https://ror.org/026v1ze26","country_code":"JP","type":"facility","lineage":["https://openalex.org/I205401836"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Luca Foppiano","raw_affiliation_strings":["National Institute for Materials Science (NIMS), Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Materials Science (NIMS), Tsukuba, Japan","institution_ids":["https://openalex.org/I205401836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045392938","display_name":"Laurent Romary","orcid":"https://orcid.org/0000-0002-0756-0508"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Romary","raw_affiliation_strings":["Inria, Paris, France"],"affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080542319","display_name":"Masashi Ishii","orcid":"https://orcid.org/0000-0003-0357-2832"},"institutions":[{"id":"https://openalex.org/I205401836","display_name":"National Institute for Materials Science","ror":"https://ror.org/026v1ze26","country_code":"JP","type":"facility","lineage":["https://openalex.org/I205401836"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Ishii","raw_affiliation_strings":["National Institute for Materials Science (NIMS), Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Materials Science (NIMS), Tsukuba, Japan","institution_ids":["https://openalex.org/I205401836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015816247","display_name":"Mikiko Tanifuji","orcid":null},"institutions":[{"id":"https://openalex.org/I205401836","display_name":"National Institute for Materials Science","ror":"https://ror.org/026v1ze26","country_code":"JP","type":"facility","lineage":["https://openalex.org/I205401836"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mikiko Tanifuji","raw_affiliation_strings":["National Institute for Materials Science (NIMS), Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Materials Science (NIMS), Tsukuba, Japan","institution_ids":["https://openalex.org/I205401836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077452892"],"corresponding_institution_ids":["https://openalex.org/I205401836"],"apc_list":null,"apc_paid":null,"fwci":1.0314,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.76395159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9972000122070312,"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":0.9972000122070312,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9969000220298767,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.7277806997299194},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6558218002319336},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5570112466812134},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48697027564048767},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4846806824207306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47588908672332764},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4653995931148529},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4271407127380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3831433057785034},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34301501512527466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32050514221191406},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19581687450408936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277806997299194},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6558218002319336},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5570112466812134},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48697027564048767},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4846806824207306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47588908672332764},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4653995931148529},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4271407127380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3831433057785034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34301501512527466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32050514221191406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19581687450408936},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3342558.3345411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02294424v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02294424","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"DocEng '19 - ACM Symposium on Document Engineering 2019, Sep 2019, Berlin, Germany. pp.1-4, ⟨10.1145/3342558.3345411⟩","raw_type":"Conference papers"},{"id":"pmh:oai:mdr.nims.go.jp:c861221b-e03e-4fc9-8cf6-8a4165174f34","is_oa":false,"landing_page_url":"https://mdr.nims.go.jp/pid/c861221b-e03e-4fc9-8cf6-8a4165174f34","pdf_url":null,"source":{"id":"https://openalex.org/S7407053566","display_name":"NIMS Materials Data Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205401836","host_organization_name":"National Institute for Materials Science","host_organization_lineage":["https://openalex.org/I205401836"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"submittedVersion"},{"id":"pmh:oai:mdr.nims.go.jp:d1fec39d-b106-4776-94c4-5f26e13e4474","is_oa":false,"landing_page_url":"https://mdr.nims.go.jp/pid/d1fec39d-b106-4776-94c4-5f26e13e4474","pdf_url":null,"source":{"id":"https://openalex.org/S7407053566","display_name":"NIMS Materials Data Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205401836","host_organization_name":"National Institute for Materials Science","host_organization_lineage":["https://openalex.org/I205401836"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"submittedVersion"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02294424v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02294424","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"DocEng '19 - ACM Symposium on Document Engineering 2019, Sep 2019, Berlin, Germany. pp.1-4, ⟨10.1145/3342558.3345411⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1603719052","https://openalex.org/W1821430800","https://openalex.org/W1968829212","https://openalex.org/W1981612367","https://openalex.org/W2002661695","https://openalex.org/W2147880316","https://openalex.org/W2406064313","https://openalex.org/W2608647994","https://openalex.org/W2945695729","https://openalex.org/W7033478570"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W2886890203","https://openalex.org/W3080906831","https://openalex.org/W1982302668","https://openalex.org/W1492005981","https://openalex.org/W3015234152","https://openalex.org/W2368651715"],"abstract_inverted_index":{"We":[0],"present":[1],"Grobid-quantities,":[2],"an":[3,200],"open-source":[4],"application":[5],"for":[6,32,55,114,176,190,224],"extracting":[7,115,177],"and":[8,13,23,35,57,120,127,153,180],"normalising":[9],"measurements":[10,137,179],"from":[11,174,217],"scientific":[12,134,218],"patent":[14],"literature.":[15],"Tools":[16],"of":[17,47,66,99,145],"this":[18],"kind,":[19],"aiming":[20],"to":[21,62,141,149,203],"understand":[22],"make":[24],"unstructured":[25],"information":[26],"accessible,":[27],"represent":[28],"the":[29,88,97,142,161,187],"building":[30],"blocks":[31],"large-scale":[33],"Text":[34],"Data":[36],"Mining":[37],"(TDM)":[38],"systems.":[39],"Grobid-quantities":[40,156],"is":[41,94,197],"a":[42,51,70,79,100,221],"module":[43],"built":[44],"on":[45],"top":[46],"Grobid":[48],"[6]":[49],"[13],":[50],"machine":[52,83],"learning":[53,84],"framework":[54],"parsing":[56],"structuring":[58],"PDF":[59],"documents.":[60],"Designed":[61],"process":[63],"large":[64],"quantities":[65,116],"data,":[67],"it":[68,196],"provides":[69],"robust":[71],"implementation":[72],"accessible":[73],"in":[74,96,164,182,193,199],"batch":[75],"mode":[76],"or":[77,133],"via":[78],"REST":[80],"API.":[81],"The":[82,103],"engine":[85,163],"architecture":[86],"follows":[87],"cascade":[89],"approach,":[90],"where":[91],"each":[92],"model":[93],"specialised":[95],"resolution":[98],"specific":[101],"task.":[102],"models":[104],"are":[105,138,220],"trained":[106],"using":[107],"CRF":[108],"(Conditional":[109],"Random":[110],"Field)":[111],"algorithm":[112],"[12]":[113],"(atomic":[117],"values,":[118],"intervals":[119],"lists),":[121],"units":[122],"(such":[123,211],"as":[124,160,169,212],"length,":[125],"weight)":[126],"different":[128],"value":[129],"representations":[130],"(numeric,":[131],"alphabetic":[132],"notation).":[135],"Identified":[136],"normalised":[139],"according":[140],"International":[143],"System":[144],"Units":[146],"(SI).":[147],"Thanks":[148],"its":[150],"stable":[151],"recall":[152],"reliable":[154],"precision,":[155],"has":[157],"been":[158],"integrated":[159],"measurement-extraction":[162],"various":[165],"TDM":[166],"projects,":[167],"such":[168],"Marve":[170],"(Measurement":[171],"Context":[172],"Extraction":[173],"Text),":[175],"semantic":[178],"meaning":[181],"Earth":[183],"Science":[184,192],"[10].":[185],"At":[186],"National":[188],"Institute":[189],"Materials":[191],"Japan":[194],"(NIMS),":[195],"used":[198],"ongoing":[201],"project":[202],"discover":[204],"new":[205],"superconducting":[206],"materials.":[207],"Normalised":[208],"materials":[209,225],"characteristics":[210],"critical":[213],"temperature,":[214],"pressure)":[215],"extracted":[216],"literature":[219],"key":[222],"resource":[223],"informatics":[226],"(MI)":[227],"[9].":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}