Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367046977> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4367046977 abstract "Temporal Knowledge Graph (TKG) is composed of a series of facts related to timestamps in the real world and has become the basis of many artificial intelligence applications. However, the existing TKG is usually incomplete. It has become a hot research task to infer missing facts based on existing facts in a TKG; namely, Temporal Knowledge Graph Completion (TKGC). The current mainstream TKGC models are embedded models that predict missing facts by representing entities, relations and timestamps as low-dimensional vectors. In order to deal with the TKG structure information, there are some models that try to introduce attention mechanism into the embedding process. But they only consider the structure information of entities or relations, and ignore the structure information of the whole TKG. Moreover, most of them usually treat timestamps as a general feature and cannot take advantage of the potential time series information of the timestamp. To solve these problems, wo propose a new Hierarchical Self-Attention Embedding (HSAE) model which inspired by self-attention mechanism and diachronic embedding technique. For structure information of the whole TKG, we divide the TKG into two layers: entity layer and relation layer, and then apply the self-attention mechanism to the entity layer and relation layer respectively to capture the structure information. For time series information of the timestamp, we capture them by combining positional encoding and diachronic embedding technique into the above two self-attention layers. Finally, we can get the embedded representation vectors of entities, relations and timestamps, which can be combined with other models for better results. We evaluate our model on three TKG datasets: ICEWS14, ICEWS05-15 and GDELT. Experimental results on the TKGC (interpolation) task demonstrate that our model achieves state-of-the-art results." @default.
- W4367046977 created "2023-04-27" @default.
- W4367046977 creator A5031842346 @default.
- W4367046977 creator A5056691786 @default.
- W4367046977 creator A5065518531 @default.
- W4367046977 creator A5069447196 @default.
- W4367046977 date "2023-04-30" @default.
- W4367046977 modified "2023-10-17" @default.
- W4367046977 title "Hierarchical Self-Attention Embedding for Temporal Knowledge Graph Completion" @default.
- W4367046977 cites W2022166150 @default.
- W4367046977 cites W2036287059 @default.
- W4367046977 cites W2251287417 @default.
- W4367046977 cites W2759136286 @default.
- W4367046977 cites W2889782235 @default.
- W4367046977 cites W2890410208 @default.
- W4367046977 cites W2911778742 @default.
- W4367046977 cites W2996899616 @default.
- W4367046977 cites W2998528434 @default.
- W4367046977 cites W3003265726 @default.
- W4367046977 cites W3100254008 @default.
- W4367046977 cites W3163457243 @default.
- W4367046977 cites W3182741322 @default.
- W4367046977 cites W3187578449 @default.
- W4367046977 cites W3199561489 @default.
- W4367046977 cites W3212669276 @default.
- W4367046977 cites W4282974123 @default.
- W4367046977 doi "https://doi.org/10.1145/3543507.3583397" @default.
- W4367046977 hasPublicationYear "2023" @default.
- W4367046977 type Work @default.
- W4367046977 citedByCount "0" @default.
- W4367046977 crossrefType "proceedings-article" @default.
- W4367046977 hasAuthorship W4367046977A5031842346 @default.
- W4367046977 hasAuthorship W4367046977A5056691786 @default.
- W4367046977 hasAuthorship W4367046977A5065518531 @default.
- W4367046977 hasAuthorship W4367046977A5069447196 @default.
- W4367046977 hasConcept C113954288 @default.
- W4367046977 hasConcept C124101348 @default.
- W4367046977 hasConcept C132525143 @default.
- W4367046977 hasConcept C154945302 @default.
- W4367046977 hasConcept C25343380 @default.
- W4367046977 hasConcept C38652104 @default.
- W4367046977 hasConcept C41008148 @default.
- W4367046977 hasConcept C41608201 @default.
- W4367046977 hasConcept C80444323 @default.
- W4367046977 hasConceptScore W4367046977C113954288 @default.
- W4367046977 hasConceptScore W4367046977C124101348 @default.
- W4367046977 hasConceptScore W4367046977C132525143 @default.
- W4367046977 hasConceptScore W4367046977C154945302 @default.
- W4367046977 hasConceptScore W4367046977C25343380 @default.
- W4367046977 hasConceptScore W4367046977C38652104 @default.
- W4367046977 hasConceptScore W4367046977C41008148 @default.
- W4367046977 hasConceptScore W4367046977C41608201 @default.
- W4367046977 hasConceptScore W4367046977C80444323 @default.
- W4367046977 hasFunder F4320321001 @default.
- W4367046977 hasFunder F4320322163 @default.
- W4367046977 hasLocation W43670469771 @default.
- W4367046977 hasOpenAccess W4367046977 @default.
- W4367046977 hasPrimaryLocation W43670469771 @default.
- W4367046977 hasRelatedWork W2551237228 @default.
- W4367046977 hasRelatedWork W2793488029 @default.
- W4367046977 hasRelatedWork W2966366588 @default.
- W4367046977 hasRelatedWork W3014537556 @default.
- W4367046977 hasRelatedWork W3035116611 @default.
- W4367046977 hasRelatedWork W4226361842 @default.
- W4367046977 hasRelatedWork W4285821569 @default.
- W4367046977 hasRelatedWork W4287763734 @default.
- W4367046977 hasRelatedWork W4307647416 @default.
- W4367046977 hasRelatedWork W3090435463 @default.
- W4367046977 isParatext "false" @default.
- W4367046977 isRetracted "false" @default.
- W4367046977 workType "article" @default.