Naslov: | Knowledge Graph Completion with Triple Structure and Text Representation |
---|
Avtorji: | ID Liu, Shuang (Avtor) ID Qin, Yufeng (Avtor) ID Xu, Man (Avtor) ID Kolmanič, Simon (Avtor) |
Datoteke: | Liu-2023-Knowledge_Graph_Completion_with_Tripl.pdf (1,03 MB) MD5: 6D6B12816525821AD6FB69DA39E97446
https://link.springer.com/article/10.1007/s44196-023-00271-0
|
---|
Jezik: | Angleški jezik |
---|
Vrsta gradiva: | Članek v reviji |
---|
Tipologija: | 1.01 - Izvirni znanstveni članek |
---|
Organizacija: | FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
|
---|
Opis: | Knowledge Graphs (KGs) describe objective facts in the form of RDF triples, each triple contains sufficient semantic information and triple structure information. Knowledge Graph Completion (KGC) is to acquire new knowledge by predicting hidden relationships between entities and adding the new knowledge to the KG. At present, the mainstream KGC approaches only applied the triple structure information or only utilized the semantic information of the text. This paper proposes an approach (TSTR) using BERT and deep neural networks to fully extract the semantic information of knowledge, and designs an aggregated re-ranking scheme that incorporates existing graph embedding approach to learn the structural information of triples. In experiments, the approach achieves state-of-the-art performance on three benchmark datasets, and outperforms recent KGC approaches on sparsely connected datasets. |
---|
Ključne besede: | knowledge graph completion, BERT, deep convolutional architecture, re-ranking |
---|
Status publikacije: | Objavljeno |
---|
Verzija publikacije: | Objavljena publikacija |
---|
Poslano v recenzijo: | 15.01.2023 |
---|
Datum sprejetja članka: | 11.05.2023 |
---|
Datum objave: | 30.05.2023 |
---|
Založnik: | Springer (Atlantis) |
---|
Leto izida: | 2023 |
---|
Št. strani: | Strr. 1-12 |
---|
Številčenje: | Letn. 16, Št. članka 95 |
---|
PID: | 20.500.12556/DKUM-87097 |
---|
UDK: | 004.9 |
---|
COBISS.SI-ID: | 162928643 |
---|
DOI: | 10.1007/s44196-023-00271-0 |
---|
ISSN pri članku: | 1875-6883 |
---|
Avtorske pravice: | © The Author(s) 2023 |
---|
Datum objave v DKUM: | 19.02.2024 |
---|
Število ogledov: | 229 |
---|
Število prenosov: | 18 |
---|
Metapodatki: | |
---|
Področja: | Ostalo
|
---|
:
|
Kopiraj citat |
---|
| | | Skupna ocena: | (0 glasov) |
---|
Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
---|
Objavi na: | |
---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |