{"id":"https://openalex.org/W7127556143","doi":null,"title":"Exploiting Unlabelled Data for Relation Extraction","display_name":"Exploiting Unlabelled Data for Relation Extraction","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W7127556143"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:studenttheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/studentTheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","pdf_url":"https://pure.manchester.ac.uk/ws/files/184625975/FULL_TEXT.PDF","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"synchronisedUnifiedStudentThesis","raw_type":"Phd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.manchester.ac.uk/ws/files/184625975/FULL_TEXT.PDF","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061574554","display_name":"Thy Thy Tran","orcid":"https://orcid.org/0000-0002-0627-9706","observed_orcids":["https://orcid.org/0000-0002-0627-9706"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tran, Thy","raw_affiliation_strings":["2020"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2020","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5061574554"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.98580002784729,"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":0.98580002784729,"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":0.010200000368058681,"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":0.0006000000284984708,"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/relation-extraction","display_name":"relation extraction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.9539999961853027},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.6800000071525574},{"id":"https://openalex.org/keywords/unsupervised-relation-extraction","display_name":"unsupervised relation extraction","score":0.921999990940094},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8270000219345093},{"id":"https://openalex.org/keywords/named-entities","display_name":"named entities","score":0.6320000290870667},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7319999933242798},{"id":"https://openalex.org/keywords/entity-types","display_name":"entity types","score":0.7200000286102295},{"id":"https://openalex.org/keywords/knowledge-base-construction","display_name":"knowledge base construction","score":0.8259999752044678}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.54830002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.375},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3059999942779541},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.atira.dk:studenttheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/studentTheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","pdf_url":"https://pure.manchester.ac.uk/ws/files/184625975/FULL_TEXT.PDF","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"synchronisedUnifiedStudentThesis","raw_type":"Phd"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:studenttheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/studentTheses/dfa41a6b-25bb-4035-9a44-ce1635cf2646","pdf_url":"https://pure.manchester.ac.uk/ws/files/184625975/FULL_TEXT.PDF","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"synchronisedUnifiedStudentThesis","raw_type":"Phd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127556143.pdf","grobid_xml":"https://content.openalex.org/works/W7127556143.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1821462560","https://openalex.org/W1838058638","https://openalex.org/W2240668419","https://openalex.org/W2525778437","https://openalex.org/W2805206884","https://openalex.org/W2898700502","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W3002104146","https://openalex.org/W3005700362","https://openalex.org/W3017231514","https://openalex.org/W3030163527","https://openalex.org/W3031177401","https://openalex.org/W3034199299","https://openalex.org/W3034709122","https://openalex.org/W3104081646","https://openalex.org/W3155682407"],"related_works":["https://openalex.org/W3163973837","https://openalex.org/W7099163133","https://openalex.org/W2900988920","https://openalex.org/W3090079961","https://openalex.org/W2927125710","https://openalex.org/W2092919065","https://openalex.org/W2986341143","https://openalex.org/W2107598941","https://openalex.org/W317603695","https://openalex.org/W2058347790"],"abstract_inverted_index":{"Information":[0],"extraction":[1,18,56,145],"transforms":[2],"unstructured":[3],"text":[4,105],"to":[5,36,94,130,163,226,240],"structured":[6],"by":[7],"annotating":[8],"semantic":[9,24],"information":[10,17,51,133,141,170],"on":[11,89,142],"raw":[12],"data.A":[13],"crucial":[14],"step":[15],"in":[16,29,46,194],"is":[19,207],"relation":[20,98,135,144,204,229],"extraction,":[21,205],"which":[22,206],"identifies":[23],"relationships":[25],"between":[26],"named":[27],"entities":[28],"text.The":[30],"resulting":[31],"relations":[32,193],"can":[33,184,247],"be":[34],"used":[35,45],"construct":[37],"and":[38,53,65,96,120],"populate":[39],"knowledge":[40],"bases":[41],"as":[42,44,50,178],"well":[43],"various":[47],"applications":[48],"such":[49,140],"retrieval":[52],"question":[54],"answering.Relation":[55],"has":[57],"been":[58],"widely":[59],"studied":[60],"using":[61,236],"fully":[62],"supervised":[63,67],"learning":[64,155],"distantly":[66],"approaches,":[68],"these":[69],"approaches":[70,250],"require":[71,215],"either":[72],"manually-or":[73,216],"automaticallyannotated":[74],"data.In":[75],"contrast,":[76],"a":[77,143,149,208],"massive":[78],"amount":[79],"of":[80,103,137],"unlabelled":[81,92,104],"texts":[82],"freely":[83],"available":[84],"are":[85,190,223],"underused.We":[86],"hence":[87,231],"focus":[88],"leveraging":[90],"the":[91,101,125,198],"data":[93],"improve":[95],"extend":[97],"extraction.We":[99,230],"approach":[100,210],"use":[102,110],"from":[106,176],"three":[107],"directions:":[108],"(i)":[109],"it":[111,212],"for":[112,134,154,192],"pre-training":[113],"word":[114,157,166],"representations,":[115],"(ii)":[116],"conduct":[117],"unsupervised":[118,203,228],"learning,":[119],"(iii)":[121],"perform":[122],"weak":[123],"supervision.Regarding":[124],"first":[126],"direction,":[127,200],"we":[128,147,183,201],"want":[129],"leverage":[131],"syntactic":[132,169],"extraction.Instead":[136],"directly":[138],"tuning":[139],"corpus,":[146],"propose":[148],"novel":[150,188],"graph":[151],"neural":[152],"model":[153],"syntactically-informed":[156],"representations.The":[158],"proposed":[159],"method":[160],"allows":[161],"us":[162],"enrich":[164],"pretrained":[165],"representations":[167,189],"with":[168],"rather":[171],"than":[172],"re-training":[173],"language":[174],"models":[175],"scratch":[177],"previous":[179],"work.Throughout":[180],"this":[181],"work,":[182],"confirm":[185],"that":[186,220],"our":[187,245],"beneficial":[191],"two":[195,233],"different":[196],"domains.In":[197],"second":[199],"study":[202],"promising":[209],"because":[211],"does":[213],"not":[214],"automatically-labelled":[217],"data.We":[218],"hypothesise":[219],"inductive":[221],"biases":[222],"extremely":[224],"important":[225],"direct":[227],"employ":[232],"simple":[234],"methods":[235,246],"only":[237],"entity":[238],"types":[239],"infer":[241],"relations.Despite":[242],"their":[243],"simplicity,":[244],"outperform":[248],"existing":[249]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-04T00:00:00"}