{"id":"https://openalex.org/W3210896084","doi":"https://doi.org/10.1145/3459637.3481936","title":"Mining Software Entities in Scientific Literature","display_name":"Mining Software Entities in Scientific Literature","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210896084","doi":"https://doi.org/10.1145/3459637.3481936","mag":"3210896084"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3481936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3481936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3481936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3481936","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009557399","display_name":"Patrice Lopez","orcid":"https://orcid.org/0000-0002-9959-9441"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Patrice Lopez","raw_affiliation_strings":["science-miner, Naves, France"],"affiliations":[{"raw_affiliation_string":"science-miner, Naves, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059105472","display_name":"Caifan Du","orcid":"https://orcid.org/0000-0003-2538-607X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caifan Du","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091768359","display_name":"Johanna Cohoon","orcid":"https://orcid.org/0000-0002-3352-9766"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johanna Cohoon","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037691598","display_name":"Karthik Ram","orcid":"https://orcid.org/0000-0002-0233-1757"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Ram","raw_affiliation_strings":["Berkeley Institute for Data Science, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Berkeley Institute for Data Science, Berkeley, CA, USA","institution_ids":["https://openalex.org/I134446601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034085206","display_name":"James Howison","orcid":"https://orcid.org/0000-0002-5702-149X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Howison","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009557399"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6998,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.76958367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3986","last_page":"3995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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":0.9977999925613403,"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/T10260","display_name":"Software Engineering Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9945999979972839,"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":0.8614877462387085},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7396171689033508},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.6644267439842224},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5854562520980835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5790080428123474},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.48619478940963745},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4528560936450958},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4466547667980194},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43856704235076904},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43752846121788025},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4154907166957855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35167521238327026},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3490201234817505},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15998145937919617},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.08481892943382263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614877462387085},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7396171689033508},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6644267439842224},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5854562520980835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5790080428123474},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.48619478940963745},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4528560936450958},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4466547667980194},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43856704235076904},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43752846121788025},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4154907166957855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35167521238327026},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3490201234817505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15998145937919617},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.08481892943382263},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3481936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3481936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3481936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3459637.3481936","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3481936","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3481936","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G906749677","display_name":null,"funder_award_id":"8622","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G930026390","display_name":null,"funder_award_id":"2016-7209","funder_id":"https://openalex.org/F4320306151","funder_display_name":"Alfred P. Sloan Foundation"}],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210896084.pdf","grobid_xml":"https://content.openalex.org/works/W3210896084.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W906769828","https://openalex.org/W1601319729","https://openalex.org/W1603719052","https://openalex.org/W1622429627","https://openalex.org/W1988157164","https://openalex.org/W2031046392","https://openalex.org/W2100627415","https://openalex.org/W2101553882","https://openalex.org/W2147880316","https://openalex.org/W2165086927","https://openalex.org/W2226221146","https://openalex.org/W2296283641","https://openalex.org/W2606280330","https://openalex.org/W2614459432","https://openalex.org/W2734608416","https://openalex.org/W2899434936","https://openalex.org/W2915623326","https://openalex.org/W2962739339","https://openalex.org/W2970771982","https://openalex.org/W2975287907","https://openalex.org/W3104748221","https://openalex.org/W3106224367","https://openalex.org/W3137946852"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W4367156293","https://openalex.org/W2750549761","https://openalex.org/W1872724644","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W2994151208","https://openalex.org/W2130894091"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,67,80],"comprehensive":[3],"information":[4],"extraction":[5],"system":[6],"dedicated":[7],"to":[8,35,70,85],"software":[9,37,51],"entities":[10],"in":[11],"scientific":[12,23],"literature.":[13],"This":[14],"task":[15,78],"combines":[16],"the":[17],"complexity":[18],"of":[19,22,44,49,56,88],"automatic":[20],"reading":[21],"documents":[24],"(PDF":[25],"processing,":[26],"document":[27],"structuring,":[28],"styled/rich":[29],"text,":[30],"scaling)":[31],"with":[32],"challenges":[33],"specific":[34],"mining":[36],"entities:":[38],"high":[39],"heterogeneity":[40],"and":[41,53,73],"extreme":[42],"sparsity":[43],"mentions,":[45],"document-level":[46],"cross-references,":[47],"disambiguation":[48],"noisy":[50],"mentions":[52],"poor":[54],"portability":[55],"Machine":[57],"Learning":[58],"approaches":[59],"between":[60],"highly":[61],"specialized":[62],"domains.":[63],"While":[64],"NER":[65,82],"is":[66],"key":[68],"component":[69],"recognize":[71],"new":[72],"unseen":[74],"software,":[75],"considering":[76],"this":[77],"as":[79],"simple":[81],"application":[83],"fails":[84],"address":[86],"most":[87],"these":[89],"issues.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
