{"id":"https://openalex.org/W4386902314","doi":"https://doi.org/10.1162/tacl_a_00592","title":"DMDD: A Large-Scale Dataset for Dataset Mentions Detection","display_name":"DMDD: A Large-Scale Dataset for Dataset Mentions Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386902314","doi":"https://doi.org/10.1162/tacl_a_00592"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00592","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00592","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00592/2159087/tacl_a_00592.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00592/2159087/tacl_a_00592.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101205186","display_name":"Huitong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huitong Pan","raw_affiliation_strings":["Temple University, Philadelphia, Pennsylvania, USA. huitong.pan@temple.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, Pennsylvania, USA. huitong.pan@temple.edu","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360395","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0235-1333"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Temple University, Philadelphia, Pennsylvania, USA. qi.zhang@temple.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, Pennsylvania, USA. qi.zhang@temple.edu","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eduard Dragut","raw_affiliation_strings":["Temple University, Philadelphia, Pennsylvania, USA. edragut@temple.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, Pennsylvania, USA. edragut@temple.edu","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["University of Illinois Chicago, Chicago, Illinois, USA. cornelia@uic.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, Illinois, USA. cornelia@uic.edu","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064854962","display_name":"Longin Jan Latecki","orcid":"https://orcid.org/0000-0002-5102-8244"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Longin Jan Latecki","raw_affiliation_strings":["Temple University, Philadelphia, Pennsylvania, USA. latecki@temple.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, Pennsylvania, USA. latecki@temple.edu","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057346703","https://openalex.org/A5064854962","https://openalex.org/A5089085275","https://openalex.org/A5100360395","https://openalex.org/A5101205186"],"corresponding_institution_ids":["https://openalex.org/I39422238","https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":1.5863,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86015042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"1132","last_page":"1146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.84687340259552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6164299249649048},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6037883162498474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4551728367805481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44525909423828125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42502155900001526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38284987211227417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84687340259552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6164299249649048},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6037883162498474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4551728367805481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44525909423828125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42502155900001526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38284987211227417},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00592","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00592","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00592/2159087/tacl_a_00592.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:30a25a27ea9146f8966be8bf0b5be8c6","is_oa":true,"landing_page_url":"https://doaj.org/article/30a25a27ea9146f8966be8bf0b5be8c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00592","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00592","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00592/2159087/tacl_a_00592.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2730730268","display_name":"III: Medium: Collaborative Research: Extracting and Linking AI Artifacts","funder_award_id":"2107213","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8131593548","display_name":"III: Medium: Collaborative Research: Extracting and Linking AI Artifacts","funder_award_id":"2107518","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312387","display_name":"Temple University","ror":"https://ror.org/00kx1jb78"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386902314.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1632114991","https://openalex.org/W2005592929","https://openalex.org/W2101410543","https://openalex.org/W2107598941","https://openalex.org/W2250539671","https://openalex.org/W2559655401","https://openalex.org/W2741447225","https://openalex.org/W2806882588","https://openalex.org/W2889399843","https://openalex.org/W2896457183","https://openalex.org/W2949181687","https://openalex.org/W2962739339","https://openalex.org/W2962903510","https://openalex.org/W2965166224","https://openalex.org/W2970320848","https://openalex.org/W2970771982","https://openalex.org/W3008889660","https://openalex.org/W3015468748","https://openalex.org/W3035372073","https://openalex.org/W3144185349","https://openalex.org/W3153386185","https://openalex.org/W3180230246","https://openalex.org/W3190588453","https://openalex.org/W3217305727","https://openalex.org/W6600347082","https://openalex.org/W6636510571","https://openalex.org/W6713197267","https://openalex.org/W6755207826","https://openalex.org/W6775750170"],"related_works":["https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W2413419736","https://openalex.org/W2786646446","https://openalex.org/W2331739042","https://openalex.org/W4238809000","https://openalex.org/W2390930322","https://openalex.org/W4256549665","https://openalex.org/W2368719721","https://openalex.org/W4386392971"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"recognition":[2],"of":[3,60,79,113],"dataset":[4,29,72,104,126,136,143],"names":[5],"is":[6],"a":[7,138],"critical":[8],"task":[9],"for":[10,28,55,93,103],"automatic":[11],"information":[12],"extraction":[13],"in":[14,34,76,125],"scientific":[15,67,89],"literature,":[16],"enabling":[17],"researchers":[18],"to":[19,99,121,133,140],"understand":[20],"and":[21,36,82,107],"identify":[22,122],"research":[23],"opportunities.":[24],"However,":[25],"existing":[26],"corpora":[27],"mention":[30,105,127,144],"detection":[31,106,145],"are":[32,119],"limited":[33],"size":[35],"naming":[37],"diversity.":[38],"In":[39],"this":[40,56],"paper,":[41],"we":[42,118],"introduce":[43],"the":[44,50,61,77,111,131],"Dataset":[45,48],"Mentions":[46],"Detection":[47],"(DMDD),":[49],"largest":[51],"publicly":[52],"available":[53],"corpus":[54],"task.":[57],"DMDD":[58,62,98],"consists":[59],"main":[63],"corpus,":[64],"comprising":[65],"31,219":[66],"articles":[68,90],"with":[69],"over":[70],"449,000":[71],"mentions":[73],"weakly":[74],"annotated":[75,92],"format":[78],"in-text":[80],"spans,":[81],"an":[83],"evaluation":[84,94],"set,":[85],"which":[86],"comprises":[87],"450":[88],"manually":[91],"purposes.":[95],"We":[96,129],"use":[97,134],"establish":[100],"baseline":[101],"performance":[102,112],"linking.":[108],"By":[109],"analyzing":[110],"various":[114],"models":[115],"on":[116],"DMDD,":[117],"able":[120],"open":[123],"problems":[124],"detection.":[128],"invite":[130],"community":[132],"our":[135],"as":[137],"challenge":[139],"develop":[141],"novel":[142],"models.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}