{"id":"https://openalex.org/W2954765265","doi":"https://doi.org/10.18653/v1/w19-5016","title":"Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns","display_name":"Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2954765265","doi":"https://doi.org/10.18653/v1/w19-5016","mag":"2954765265"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5016","pdf_url":"https://www.aclweb.org/anthology/W19-5016.pdf","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 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5016.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082220190","display_name":"Julien Fauqueur","orcid":"https://orcid.org/0000-0003-0227-2221"},"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":true,"raw_author_name":"Julien Fauqueur","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076733967","display_name":"Ashok Thillaisundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122598","display_name":"BenevolentAI (United Kingdom)","ror":"https://ror.org/02z480994","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210122598"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashok Thillaisundaram","raw_affiliation_strings":["BenevolentAI"],"affiliations":[{"raw_affiliation_string":"BenevolentAI","institution_ids":["https://openalex.org/I4210122598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000069717","display_name":"Theodosia Togia","orcid":null},"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":"Theodosia Togia","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082220190"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.6851,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68939401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9973000288009644,"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":0.7055087089538574},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6242246031761169},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6116757988929749},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5440929532051086},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.5329210758209229},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5264873504638672},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4827558398246765},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4660799205303192},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46578019857406616},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4615080654621124},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.45602744817733765},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4336223900318146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4296032190322876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41860106587409973},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3883051574230194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11792653799057007},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0869189202785492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7055087089538574},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6242246031761169},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6116757988929749},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5440929532051086},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5329210758209229},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5264873504638672},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4827558398246765},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4660799205303192},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46578019857406616},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4615080654621124},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.45602744817733765},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4336223900318146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4296032190322876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41860106587409973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3883051574230194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11792653799057007},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0869189202785492},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5016","pdf_url":"https://www.aclweb.org/anthology/W19-5016.pdf","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 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.01417","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01417","pdf_url":"https://arxiv.org/pdf/1907.01417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2954765265","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1907.01417.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.01417","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.01417","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5016","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5016","pdf_url":"https://www.aclweb.org/anthology/W19-5016.pdf","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 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954765265.pdf","grobid_xml":"https://content.openalex.org/works/W2954765265.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W180510140","https://openalex.org/W1493490255","https://openalex.org/W1905066734","https://openalex.org/W2081580037","https://openalex.org/W2083545228","https://openalex.org/W2103931177","https://openalex.org/W2109718074","https://openalex.org/W2117173982","https://openalex.org/W2129842875","https://openalex.org/W2146960529","https://openalex.org/W2167187514","https://openalex.org/W2251913848","https://openalex.org/W2515462165","https://openalex.org/W2766208765","https://openalex.org/W2911424454","https://openalex.org/W2962915384","https://openalex.org/W2962936385"],"related_works":["https://openalex.org/W2970137004","https://openalex.org/W2463552202","https://openalex.org/W2399992781","https://openalex.org/W2609287048","https://openalex.org/W2293210525","https://openalex.org/W2952213506","https://openalex.org/W2071553179","https://openalex.org/W2800736402","https://openalex.org/W3184533700","https://openalex.org/W1565178299","https://openalex.org/W2334964302","https://openalex.org/W1572890417","https://openalex.org/W2186949642","https://openalex.org/W3132322306","https://openalex.org/W2953100092","https://openalex.org/W3108445278","https://openalex.org/W2295861738","https://openalex.org/W2240456204","https://openalex.org/W1900641977","https://openalex.org/W2983475513"],"abstract_inverted_index":{"Knowledge":[0],"base":[1,317],"construction":[2],"is":[3,31,124,168,174,230,324],"crucial":[4],"for":[5,15,34,248,260,264,276,295],"summarising,":[6],"understanding":[7],"and":[8,65,94,220,234,243,250,263,285,299,311,313,320],"inferring":[9],"relationships":[10],"between":[11],"biomedical":[12,80],"entities.":[13],"However,":[14],"many":[16],"practical":[17],"applications":[18],"such":[19,127],"as":[20,110],"drug":[21],"discovery,":[22],"the":[23,79,96,113,130,150,181,198,236,240,245,258,265,269,274,277,282,288,296,301,307,314],"scarcity":[24],"of":[25,68,137,146,159,183,197,328],"relevant":[26,160,336],"facts":[27,71,337],"(e.g.":[28,171],"gene":[29,172],"X":[30,173],"therapeutic":[32],"target":[33],"disease":[35,178],"Y)":[36,179],"severely":[37],"limits":[38],"a":[39,45,54,63,73,134,156,194,210,222],"domain":[40,101],"expert's":[41],"ability":[42],"to":[43,100,143,191,200],"create":[44],"usable":[46],"knowledge":[47,224,330],"base,":[48],"either":[49],"directly":[50],"or":[51,87,203,334],"by":[52],"training":[53,85],"relation":[55],"extraction":[56,271],"model.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"present":[62],"simple":[64],"effective":[66,326],"method":[67,217],"extracting":[69,249],"new":[70],"with":[72,112,126,133,149,177,306],"pre-specified":[74],"binary":[75],"relationship":[76,115,123,152,167,182],"type":[77],"from":[78],"literature,":[81],"without":[82],"requiring":[83],"any":[84],"data":[86],"hand-crafted":[88],"rules.":[89],"Our":[90],"system":[91,186,297],"discovers,":[92],"ranks":[93],"presents":[95],"most":[97],"salient":[98],"patterns":[99,109,128,199],"experts":[102,117,140],"in":[103,129,189,209],"an":[104,325],"interpretable":[105],"form.":[106],"By":[107],"marking":[108],"compatible":[111],"desired":[114,151],"type,":[116],"indirectly":[118],"batch-annotate":[119],"candidate":[120],"pairs":[121,148,161,208],"whose":[122],"expressed":[125],"literature.":[131],"Even":[132],"complete":[135],"absence":[136],"seed":[138],"data,":[139],"are":[141,338],"able":[142],"discover":[144],"thousands":[145],"high-quality":[147],"within":[153],"minutes.":[154],"When":[155],"small":[157],"number":[158],"do":[162],"exist":[163],"-even":[164],"when":[165,332],"their":[166],"more":[169],"general":[170],"biologically":[175],"associated":[176],"than":[180],"interest":[184],"-our":[185],"leverages":[187],"them":[188],"order":[190,229],"i)":[192],"learn":[193],"better":[195],"ranking":[196,261],"be":[201],"annotated":[202],"ii)":[204],"generate":[205],"weakly":[206],"labelled":[207],"fully":[211],"automated":[212,278],"manner.":[213],"We":[214],"evaluate":[215],"our":[216],"both":[218],"intrinsically":[219],"via":[221],"downstream":[223],"*":[225],"Equal":[226],"contribution.":[227],"Listing":[228],"alphabetical.":[231],"Theodosia":[232],"proposed":[233],"co-ordinated":[235],"research":[237],"project,":[238],"built":[239],"early":[241],"prototypes":[242],"contributed":[244],"different":[246],"methods":[247],"lexicalising":[251],"patterns.":[252],"Ashok":[253],"provided":[254],"conceptual":[255],"work":[256],"on":[257],"metrics":[259],"simplifications":[262],"intrinsic":[266,302],"evaluation,":[267],"developed":[268],"simplification":[270],"module,":[272],"ran":[273],"experiments":[275],"workflow":[279],"(with":[280],"all":[281,287],"parameter":[283],"variations)":[284],"performed":[286],"extrinsic":[289],"evaluations.":[290],"Julien":[291],"was":[292],"mainly":[293],"responsible":[294],"architecture":[298],"workflow,":[300],"evaluation":[303],"(including":[304],"interacting":[305],"experts),":[308],"handling":[309],"negation":[310],"speculation":[312],"clustering":[315],"algorithm.":[316],"completion":[318],"task,":[319],"show":[321],"that":[322],"it":[323],"way":[327],"constructing":[329],"bases":[331],"few":[333],"no":[335],"already":[339],"available.":[340]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}