{"id":"https://openalex.org/W3216667583","doi":"https://doi.org/10.1162/tacl_a_00456","title":"Predicting Document Coverage for Relation Extraction","display_name":"Predicting Document Coverage for Relation Extraction","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3216667583","doi":"https://doi.org/10.1162/tacl_a_00456","mag":"3216667583"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00456","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00456","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00456/2002678/tacl_a_00456.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_00456/2002678/tacl_a_00456.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059897786","display_name":"Sneha Singhania","orcid":"https://orcid.org/0000-0002-2803-9973"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sneha Singhania","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany. ssinghan@mpi-inf.mpg.de\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany. ssinghan@mpi-inf.mpg.de\"","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058717031","display_name":"Simon Razniewski","orcid":"https://orcid.org/0000-0002-5410-218X"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simon Razniewski","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany. srazniew@mpi-inf.mpg.de\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany. srazniew@mpi-inf.mpg.de\"","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gerhard Weikum","raw_affiliation_strings":["Max Planck Institute for Informatics, Germany. weikum@mpi-inf.mpg.de\""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Germany. weikum@mpi-inf.mpg.de\"","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058717031","https://openalex.org/A5059897786","https://openalex.org/A5088135366"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58038828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"207","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9026978015899658},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.7040932178497314},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6089915037155151},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.608677864074707},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5898388624191284},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5699475407600403},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5577566027641296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5546850562095642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490319728851318},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4607366919517517},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4482842683792114},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.41190996766090393},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3096494674682617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9026978015899658},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.7040932178497314},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6089915037155151},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.608677864074707},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5898388624191284},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5699475407600403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5577566027641296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5546850562095642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490319728851318},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4607366919517517},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4482842683792114},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.41190996766090393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3096494674682617},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00456","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00456","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00456/2002678/tacl_a_00456.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:816dd55b78d3425289c58a218f65dc07","is_oa":false,"landing_page_url":"https://doaj.org/article/816dd55b78d3425289c58a218f65dc07","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 10 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00456","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00456","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00456/2002678/tacl_a_00456.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":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6013706260","display_name":null,"funder_award_id":"4530095897","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3216667583.pdf","grobid_xml":"https://content.openalex.org/works/W3216667583.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W16121876","https://openalex.org/W61851215","https://openalex.org/W277886906","https://openalex.org/W1481281556","https://openalex.org/W1482214997","https://openalex.org/W1604644367","https://openalex.org/W1880262756","https://openalex.org/W1975879668","https://openalex.org/W2064675550","https://openalex.org/W2069870183","https://openalex.org/W2107598941","https://openalex.org/W2155737120","https://openalex.org/W2250293237","https://openalex.org/W2250539671","https://openalex.org/W2515462165","https://openalex.org/W2581102923","https://openalex.org/W2759211898","https://openalex.org/W2759820691","https://openalex.org/W2887107689","https://openalex.org/W2909544278","https://openalex.org/W2945127593","https://openalex.org/W2946364534","https://openalex.org/W2951056191","https://openalex.org/W2952179106","https://openalex.org/W2962849707","https://openalex.org/W2963341956","https://openalex.org/W2963360277","https://openalex.org/W2963961878","https://openalex.org/W2964022985","https://openalex.org/W2971186714","https://openalex.org/W2979222811","https://openalex.org/W3010336026","https://openalex.org/W3031414848","https://openalex.org/W3082274269","https://openalex.org/W3099067526","https://openalex.org/W3099446234","https://openalex.org/W3100107515","https://openalex.org/W3115294291","https://openalex.org/W3131978031","https://openalex.org/W3158986179","https://openalex.org/W3173229273","https://openalex.org/W3180536457","https://openalex.org/W3199223649","https://openalex.org/W4231510805","https://openalex.org/W4288089799","https://openalex.org/W4300427681","https://openalex.org/W4404783772","https://openalex.org/W6628905179","https://openalex.org/W6639619044","https://openalex.org/W6755207826","https://openalex.org/W6758015726","https://openalex.org/W6763331066","https://openalex.org/W6769627184","https://openalex.org/W6775699949","https://openalex.org/W6778821473","https://openalex.org/W6795224213"],"related_works":["https://openalex.org/W2444550338","https://openalex.org/W2798237655","https://openalex.org/W4287888486","https://openalex.org/W2129842875","https://openalex.org/W2750803316","https://openalex.org/W2904639846","https://openalex.org/W2131778685","https://openalex.org/W3185688007","https://openalex.org/W4225278886","https://openalex.org/W3114114934"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"presents":[3],"a":[4,12,27,53],"new":[5],"task":[6],"of":[7,11,55,66,85,119,127],"predicting":[8],"the":[9,20,36,64,125],"coverage":[10,68,128],"text":[13],"document":[14,21,67],"for":[15,26,39,59],"relation":[16],"extraction":[17],"(RE):":[18],"Does":[19],"contain":[22],"many":[23],"relational":[24],"tuples":[25],"given":[28],"entity?":[29],"Coverage":[30],"predictions":[31,129],"are":[32],"useful":[33],"in":[34],"selecting":[35],"best":[37],"documents":[38,58],"knowledge":[40],"base":[41],"construction":[42,135],"with":[43,69,98],"large":[44],"input":[45],"corpora.":[46],"To":[47],"study":[48],"this":[49],"problem,":[50],"we":[51],"present":[52],"dataset":[54],"31,366":[56],"diverse":[57],"520":[60],"entities.":[61],"We":[62,93,123],"analyze":[63],"correlation":[65],"features":[70,87,97,111],"like":[71,101,106],"length,":[72],"entity":[73],"mention":[74],"frequency,":[75],"Alexa":[76],"rank,":[77],"language":[78,104],"complexity,":[79],"and":[80,103,112,136],"information":[81],"retrieval":[82],"scores.":[83],"Each":[84],"these":[86],"has":[88],"only":[89],"moderate":[90],"predictive":[91],"power.":[92],"employ":[94],"methods":[95],"combining":[96,110],"statistical":[99],"models":[100,105],"TF-IDF":[102],"BERT.":[107],"The":[108],"model":[109],"BERT,":[113],"HERB,":[114],"achieves":[115],"an":[116],"F1":[117],"score":[118],"up":[120],"to":[121],"46%.":[122],"demonstrate":[124],"utility":[126],"on":[130],"two":[131],"use":[132],"cases:":[133],"KB":[134],"claim":[137],"refutation.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}