{"id":"https://openalex.org/W3130909864","doi":"https://doi.org/10.1145/3442381.3450043","title":"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion","display_name":"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3130909864","doi":"https://doi.org/10.1145/3442381.3450043","mag":"3130909864"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3450043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450043","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3450043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Wang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I2802355861","display_name":"Australian Institute of Business","ror":"https://ror.org/01wf5jq34","country_code":"AU","type":"education","lineage":["https://openalex.org/I2802355861"]},{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Shen","raw_affiliation_strings":["Australian AI Institute, School of CS, FEIT, University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of CS, FEIT, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I2802355861","https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guodong Long","orcid":null},"institutions":[{"id":"https://openalex.org/I2802355861","display_name":"Australian Institute of Business","ror":"https://ror.org/01wf5jq34","country_code":"AU","type":"education","lineage":["https://openalex.org/I2802355861"]},{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guodong Long","raw_affiliation_strings":["Australian AI Institute, School of CS, FEIT, University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Australian AI Institute, School of CS, FEIT, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I2802355861","https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhou","raw_affiliation_strings":["Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yi Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University and International Center of Future Science, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University and International Center of Future Science, Jilin University, China","institution_ids":["https://openalex.org/I4210164189","https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":19.1509,"has_fulltext":false,"cited_by_count":191,"citation_normalized_percentile":{"value":0.99461124,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1737","last_page":"1748"},"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/T11273","display_name":"Advanced Graph Neural Networks","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/embedding","display_name":"Embedding","score":0.6794999837875366},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5177000164985657},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5121999979019165},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4887999892234802},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.4684000015258789},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.38359999656677246},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3774000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064999938011169},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5339999794960022},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5177000164985657},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.4684000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648999869823456},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.362199991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C157406716","wikidata":"https://www.wikidata.org/wiki/Q4115842","display_name":"Topological graph theory","level":5,"score":0.28519999980926514},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C54540088","wikidata":"https://www.wikidata.org/wiki/Q3498041","display_name":"Intersection graph","level":4,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3442381.3450043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450043","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.14781","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14781","pdf_url":"https://arxiv.org/pdf/2004.14781","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"}],"best_oa_location":{"id":"doi:10.1145/3442381.3450043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450043","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2022166150","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2157364932","https://openalex.org/W2158028897","https://openalex.org/W2250539671","https://openalex.org/W2250635077","https://openalex.org/W2336384382","https://openalex.org/W2509893387","https://openalex.org/W2558476738","https://openalex.org/W2604165577","https://openalex.org/W2604314403","https://openalex.org/W2728059831","https://openalex.org/W2774837955","https://openalex.org/W2889234142","https://openalex.org/W2914592219","https://openalex.org/W2951105272","https://openalex.org/W2962739339","https://openalex.org/W2963041663","https://openalex.org/W2963217826","https://openalex.org/W2963341956","https://openalex.org/W2963485453","https://openalex.org/W2963855739","https://openalex.org/W2964279602","https://openalex.org/W2970641574","https://openalex.org/W2971167006","https://openalex.org/W3034374701","https://openalex.org/W3035134435"],"related_works":[],"abstract_inverted_index":{"Human-curated":[0],"knowledge":[1,24,35,130,227],"graphs":[2,15],"provide":[3],"critical":[4],"supportive":[5],"information":[6],"to":[7,58,69,80,94,114,146,220,240,283],"various":[8],"natural":[9],"language":[10],"processing":[11],"tasks,":[12],"but":[13],"these":[14],"are":[16,55,66,89],"usually":[17],"incomplete,":[18],"urging":[19],"auto-completion":[20],"of":[21,118,128,161,273,280],"them":[22],"(a.k.a.":[23],"graph":[25,28,38,70,81,154,176,217,252],"completion).":[26],"Prevalent":[27],"embedding":[29,155,177,253],"approaches,":[30,76],"e.g.,":[31,77],"TransE,":[32],"learn":[33],"structured":[34,129,226],"via":[36],"representing":[37],"elements":[39,60],"(i.e.,":[40],"entities/relations)":[41],"into":[42,169,183],"dense":[43],"embeddings":[44,219],"and":[45,65,84,92,124,144,179,201,206,224,264],"capturing":[46],"their":[47],"triple-level":[48,85],"relationship":[49],"with":[50,100,153,271],"spatial":[51,202,231],"distance.":[52],"However,":[53],"they":[54],"hardly":[56],"generalizable":[57,90],"the":[59,95,108,115,132,140,193,213,230,243],"never":[61],"visited":[62],"in":[63,122,131,174],"training":[64],"intrinsically":[67],"vulnerable":[68],"incompleteness.":[71],"In":[72,135,255],"contrast,":[73],"textual":[74,133,141,189,286],"encoding":[75,142,287],"KG-BERT,":[78],"resort":[79],"triple\u2019s":[82],"text":[83],"contextualized":[86,184],"representations.":[87],"They":[88],"enough":[91],"robust":[93],"incompleteness,":[96],"especially":[97],"when":[98],"coupled":[99],"pre-trained":[101],"encoders.":[102],"But":[103],"two":[104,170],"major":[105],"drawbacks":[106,149],"limit":[107],"performance:":[109],"(1)":[110],"high":[111],"overheads":[112,214],"due":[113],"costly":[116],"scoring":[117],"all":[119],"possible":[120],"triples":[121],"inference,":[123],"(2)":[125],"a":[126,158,187,236,265,284],"lack":[127],"encoder.":[134,190],"this":[136],"paper,":[137],"we":[138,165,234,257],"follow":[139],"paradigm":[143],"aim":[145],"alleviate":[147],"its":[148],"by":[150,186,215,228,245,277],"augmenting":[151],"it":[152],"techniques":[156],"\u2013":[157],"complementary":[159],"hybrid":[160],"both":[162,181,198],"paradigms.":[163],"Specifically,":[164],"partition":[166],"each":[167],"triple":[168,247],"asymmetric":[171],"parts":[172,182],"as":[173],"translation-based":[175],"approach,":[178],"encode":[180],"representations":[185],"Siamese-style":[188],"Built":[191],"upon":[192],"representations,":[194],"our":[195],"model":[196],"employs":[197],"deterministic":[199],"classifier":[200],"measurement":[203],"for":[204,268],"representation":[205],"structure":[207],"learning":[208],"respectively.":[209],"It":[210],"thus":[211],"reduces":[212],"reusing":[216],"elements\u2019":[218],"avoid":[221],"combinatorial":[222],"explosion,":[223],"enhances":[225],"exploring":[229],"characteristics.":[232],"Moreover,":[233],"develop":[235],"self-adaptive":[237],"ensemble":[238],"scheme":[239],"further":[241],"improve":[242],"performance":[244,260],"incorporating":[246],"scores":[248],"from":[249],"an":[250],"existing":[251],"model.":[254],"experiments,":[256],"achieve":[258],"state-of-the-art":[259],"on":[261],"three":[262],"benchmarks":[263],"zero-shot":[266],"dataset":[267],"link":[269],"prediction,":[270],"highlights":[272],"inference":[274],"costs":[275],"reduced":[276],"1-2":[278],"orders":[279],"magnitude":[281],"compared":[282],"sophisticated":[285],"method.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":63},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2021-03-01T00:00:00"}