Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312596239> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4312596239 abstract "Multi-hop Question Answering using the knowledge graph (KG) as a data source requires subject entities and relations that are obtained from natural language questions; the answers are then obtained by reasoning through multiple triples in the KG. However, even large KGs are incomplete, and the reasoning often fails to obtain the correct answer due to the lack of relations in the KG. Recently, researchers have proposed introducing KG embedding into the multi-hop knowledge graph question answering (KGQA) field to solve the incompleteness of the KG. However, these methods embed the question and the KG into different semantic spaces, and it is difficult to obtain the correct answers. Furthermore, due to the limitation of the question embedding sequence, the contribution of each word to the question semantics cannot be distinguished. To overcome the above problems, this paper proposes an effective multi-hop KGQA model, TIPNet, using relation embeddings in knowledge graph triples, which uses the idea of translation models to narrow the semantic spatial distance between question embeddings and KG embeddings. At the same time, TIP weighting technology is proposed to distinguish the semantic contribution of words to the question. To validate the performance of TIPNet, experiments were conducted on the WebQSP and CWQ datasets, and the model reached advanced levels under both KG-full and KG-half settings." @default.
- W4312596239 created "2023-01-05" @default.
- W4312596239 creator A5000400480 @default.
- W4312596239 creator A5005752135 @default.
- W4312596239 creator A5054884987 @default.
- W4312596239 date "2022-07-18" @default.
- W4312596239 modified "2023-09-27" @default.
- W4312596239 title "Multi-hop Question Answering with Knowledge Graph Embedding in a Similar Semantic Space" @default.
- W4312596239 cites W1512387364 @default.
- W4312596239 cites W2016753842 @default.
- W4312596239 cites W2022166150 @default.
- W4312596239 cites W2094728533 @default.
- W4312596239 cites W2184957013 @default.
- W4312596239 cites W2250342289 @default.
- W4312596239 cites W2283196293 @default.
- W4312596239 cites W2511149293 @default.
- W4312596239 cites W2622701666 @default.
- W4312596239 cites W2755637027 @default.
- W4312596239 cites W277886906 @default.
- W4312596239 cites W2804452021 @default.
- W4312596239 cites W2945844671 @default.
- W4312596239 cites W2963209464 @default.
- W4312596239 cites W2963448850 @default.
- W4312596239 cites W2964120615 @default.
- W4312596239 cites W2981039167 @default.
- W4312596239 cites W2996919866 @default.
- W4312596239 cites W3034862985 @default.
- W4312596239 cites W3116847845 @default.
- W4312596239 cites W3155676782 @default.
- W4312596239 cites W3156128319 @default.
- W4312596239 doi "https://doi.org/10.1109/ijcnn55064.2022.9892550" @default.
- W4312596239 hasPublicationYear "2022" @default.
- W4312596239 type Work @default.
- W4312596239 citedByCount "1" @default.
- W4312596239 countsByYear W43125962392023 @default.
- W4312596239 crossrefType "proceedings-article" @default.
- W4312596239 hasAuthorship W4312596239A5000400480 @default.
- W4312596239 hasAuthorship W4312596239A5005752135 @default.
- W4312596239 hasAuthorship W4312596239A5054884987 @default.
- W4312596239 hasConcept C126838900 @default.
- W4312596239 hasConcept C132525143 @default.
- W4312596239 hasConcept C154945302 @default.
- W4312596239 hasConcept C183115368 @default.
- W4312596239 hasConcept C204321447 @default.
- W4312596239 hasConcept C23123220 @default.
- W4312596239 hasConcept C2777462759 @default.
- W4312596239 hasConcept C2987255567 @default.
- W4312596239 hasConcept C41008148 @default.
- W4312596239 hasConcept C41608201 @default.
- W4312596239 hasConcept C44291984 @default.
- W4312596239 hasConcept C71924100 @default.
- W4312596239 hasConcept C80444323 @default.
- W4312596239 hasConceptScore W4312596239C126838900 @default.
- W4312596239 hasConceptScore W4312596239C132525143 @default.
- W4312596239 hasConceptScore W4312596239C154945302 @default.
- W4312596239 hasConceptScore W4312596239C183115368 @default.
- W4312596239 hasConceptScore W4312596239C204321447 @default.
- W4312596239 hasConceptScore W4312596239C23123220 @default.
- W4312596239 hasConceptScore W4312596239C2777462759 @default.
- W4312596239 hasConceptScore W4312596239C2987255567 @default.
- W4312596239 hasConceptScore W4312596239C41008148 @default.
- W4312596239 hasConceptScore W4312596239C41608201 @default.
- W4312596239 hasConceptScore W4312596239C44291984 @default.
- W4312596239 hasConceptScore W4312596239C71924100 @default.
- W4312596239 hasConceptScore W4312596239C80444323 @default.
- W4312596239 hasLocation W43125962391 @default.
- W4312596239 hasOpenAccess W4312596239 @default.
- W4312596239 hasPrimaryLocation W43125962391 @default.
- W4312596239 hasRelatedWork W2398825887 @default.
- W4312596239 hasRelatedWork W2923818335 @default.
- W4312596239 hasRelatedWork W3105055517 @default.
- W4312596239 hasRelatedWork W4206939502 @default.
- W4312596239 hasRelatedWork W4226361842 @default.
- W4312596239 hasRelatedWork W4310879833 @default.
- W4312596239 hasRelatedWork W4312327654 @default.
- W4312596239 hasRelatedWork W4312937211 @default.
- W4312596239 hasRelatedWork W4321601374 @default.
- W4312596239 hasRelatedWork W4323362462 @default.
- W4312596239 isParatext "false" @default.
- W4312596239 isRetracted "false" @default.
- W4312596239 workType "article" @default.