Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385482693> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4385482693 abstract "Event detection (ED) is a key subtask of information extraction to extract key events, such as stock rise and fall and social public opinion, from news or social media. Although current GCN-based event detection methods achieve remarkable success via building graphs with dependency trees, they typically suffer from two challenges: 1) They use sequence models to learn contextual information of sentences, ignoring the longterm dependencies problem of sequence models might learn ineffective information and make it propagate in GCN layers. 2) Most methods do not exploit global dependency label information and grammatical structure information that convey rich linguistic knowledge directly, and only consider local dependency label information. To cope with these challenges, we propose a novel event detection model via semantic-reconstructed graph transformer networks (SRGTNED), which incorporates semantic reconstruction and path information collection methods. Using the semantic reconstruction method, we assign a pruned sequence to each word based on the path information to capture contextual information consistent with sentence semantics. Moreover, to better utilize global dependency label information and grammatical structure information, a Graph Transformer Network (GTN)-based heterogeneous graph embedding framework is introduced to automatically learn path information between important words by converting sentences as heterogeneous graphs. We conduct experiments on the ACE2005 dataset and the Commodity News dataset, and the experimental results demonstrate that our method significantly outperforms 11 state-of-the-art baselines in terms of the F1-score." @default.
- W4385482693 created "2023-08-03" @default.
- W4385482693 creator A5041959147 @default.
- W4385482693 creator A5059939190 @default.
- W4385482693 creator A5062592193 @default.
- W4385482693 creator A5089102643 @default.
- W4385482693 date "2023-06-18" @default.
- W4385482693 modified "2023-09-26" @default.
- W4385482693 title "Semantic-Reconstructed Graph Transformer Network for Event Detection" @default.
- W4385482693 cites W2005676288 @default.
- W4385482693 cites W2090891622 @default.
- W4385482693 cites W2134486566 @default.
- W4385482693 cites W2250575108 @default.
- W4385482693 cites W2250999640 @default.
- W4385482693 cites W2475245295 @default.
- W4385482693 cites W2606202972 @default.
- W4385482693 cites W2618285232 @default.
- W4385482693 cites W2739918945 @default.
- W4385482693 cites W2788474500 @default.
- W4385482693 cites W2788525741 @default.
- W4385482693 cites W2798563357 @default.
- W4385482693 cites W2891553865 @default.
- W4385482693 cites W2946760275 @default.
- W4385482693 cites W2970763364 @default.
- W4385482693 cites W2997636257 @default.
- W4385482693 cites W3034618665 @default.
- W4385482693 cites W3035000929 @default.
- W4385482693 cites W3092574271 @default.
- W4385482693 cites W3098881736 @default.
- W4385482693 cites W3101701554 @default.
- W4385482693 cites W3114928288 @default.
- W4385482693 cites W3174505712 @default.
- W4385482693 cites W3211807332 @default.
- W4385482693 cites W3212482672 @default.
- W4385482693 cites W4312252283 @default.
- W4385482693 doi "https://doi.org/10.1109/ijcnn54540.2023.10191893" @default.
- W4385482693 hasPublicationYear "2023" @default.
- W4385482693 type Work @default.
- W4385482693 citedByCount "0" @default.
- W4385482693 crossrefType "proceedings-article" @default.
- W4385482693 hasAuthorship W4385482693A5041959147 @default.
- W4385482693 hasAuthorship W4385482693A5059939190 @default.
- W4385482693 hasAuthorship W4385482693A5062592193 @default.
- W4385482693 hasAuthorship W4385482693A5089102643 @default.
- W4385482693 hasConcept C119857082 @default.
- W4385482693 hasConcept C121332964 @default.
- W4385482693 hasConcept C124101348 @default.
- W4385482693 hasConcept C132525143 @default.
- W4385482693 hasConcept C154945302 @default.
- W4385482693 hasConcept C16311509 @default.
- W4385482693 hasConcept C165696696 @default.
- W4385482693 hasConcept C165801399 @default.
- W4385482693 hasConcept C204321447 @default.
- W4385482693 hasConcept C2777462759 @default.
- W4385482693 hasConcept C2777530160 @default.
- W4385482693 hasConcept C38652104 @default.
- W4385482693 hasConcept C41008148 @default.
- W4385482693 hasConcept C41608201 @default.
- W4385482693 hasConcept C62520636 @default.
- W4385482693 hasConcept C66322947 @default.
- W4385482693 hasConcept C80444323 @default.
- W4385482693 hasConceptScore W4385482693C119857082 @default.
- W4385482693 hasConceptScore W4385482693C121332964 @default.
- W4385482693 hasConceptScore W4385482693C124101348 @default.
- W4385482693 hasConceptScore W4385482693C132525143 @default.
- W4385482693 hasConceptScore W4385482693C154945302 @default.
- W4385482693 hasConceptScore W4385482693C16311509 @default.
- W4385482693 hasConceptScore W4385482693C165696696 @default.
- W4385482693 hasConceptScore W4385482693C165801399 @default.
- W4385482693 hasConceptScore W4385482693C204321447 @default.
- W4385482693 hasConceptScore W4385482693C2777462759 @default.
- W4385482693 hasConceptScore W4385482693C2777530160 @default.
- W4385482693 hasConceptScore W4385482693C38652104 @default.
- W4385482693 hasConceptScore W4385482693C41008148 @default.
- W4385482693 hasConceptScore W4385482693C41608201 @default.
- W4385482693 hasConceptScore W4385482693C62520636 @default.
- W4385482693 hasConceptScore W4385482693C66322947 @default.
- W4385482693 hasConceptScore W4385482693C80444323 @default.
- W4385482693 hasFunder F4320321001 @default.
- W4385482693 hasFunder F4320335787 @default.
- W4385482693 hasLocation W43854826931 @default.
- W4385482693 hasOpenAccess W4385482693 @default.
- W4385482693 hasPrimaryLocation W43854826931 @default.
- W4385482693 hasRelatedWork W159132833 @default.
- W4385482693 hasRelatedWork W2886767593 @default.
- W4385482693 hasRelatedWork W3134737443 @default.
- W4385482693 hasRelatedWork W3163043986 @default.
- W4385482693 hasRelatedWork W3212418102 @default.
- W4385482693 hasRelatedWork W4312046383 @default.
- W4385482693 hasRelatedWork W4318978824 @default.
- W4385482693 hasRelatedWork W4323060038 @default.
- W4385482693 hasRelatedWork W4385873483 @default.
- W4385482693 hasRelatedWork W4385877744 @default.
- W4385482693 isParatext "false" @default.
- W4385482693 isRetracted "false" @default.
- W4385482693 workType "article" @default.