Matches in SemOpenAlex for { <https://semopenalex.org/work/W3189979155> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3189979155 abstract "Learning to order events at discourse-level is a crucial text understanding task. Despite many efforts for this task, the current state-of-the-art methods rely heavily on manually designed features, which are costly to produce and are often specific to tasks/domains/datasets. In this paper, we propose a new graph perspective on the task, which does not require complex feature engineering but can assimilate global features and learn inter-dependencies effectively. Specifically, in our approach, each document is considered as a temporal graph, in which the nodes and edges represent events and event-event relations respectively. In this sense, the temporal ordering task corresponds to constructing edges for an empty graph. To train our model, we design a graph mask pre-training mechanism, which can learn inter-dependencies of temporal relations by learning to recover a masked edge following graph topology. In the testing stage, we design an certain-first strategy based on model uncertainty, which can decide the prediction orders and reduce the risk of error propagation. The experimental results demonstrate that our approach outperforms previous methods consistently and can meanwhile maintain good global consistency." @default.
- W3189979155 created "2021-08-16" @default.
- W3189979155 creator A5043896172 @default.
- W3189979155 creator A5047932411 @default.
- W3189979155 creator A5058555426 @default.
- W3189979155 creator A5064663972 @default.
- W3189979155 date "2021-08-01" @default.
- W3189979155 modified "2023-10-16" @default.
- W3189979155 title "Discourse-Level Event Temporal Ordering with Uncertainty-Guided Graph Completion" @default.
- W3189979155 cites W1619424147 @default.
- W3189979155 cites W2098844768 @default.
- W3189979155 cites W2109308402 @default.
- W3189979155 cites W2122540544 @default.
- W3189979155 cites W2185599447 @default.
- W3189979155 cites W2250539671 @default.
- W3189979155 cites W2251325107 @default.
- W3189979155 cites W2251758222 @default.
- W3189979155 cites W2600702321 @default.
- W3189979155 cites W2741237963 @default.
- W3189979155 cites W2760579680 @default.
- W3189979155 cites W2798865369 @default.
- W3189979155 cites W2892094955 @default.
- W3189979155 cites W2963341956 @default.
- W3189979155 cites W2964059111 @default.
- W3189979155 cites W2964121744 @default.
- W3189979155 cites W2971036674 @default.
- W3189979155 cites W2971236147 @default.
- W3189979155 cites W30314283 @default.
- W3189979155 cites W3102554291 @default.
- W3189979155 doi "https://doi.org/10.24963/ijcai.2021/533" @default.
- W3189979155 hasPublicationYear "2021" @default.
- W3189979155 type Work @default.
- W3189979155 sameAs 3189979155 @default.
- W3189979155 citedByCount "6" @default.
- W3189979155 countsByYear W31899791552022 @default.
- W3189979155 countsByYear W31899791552023 @default.
- W3189979155 crossrefType "proceedings-article" @default.
- W3189979155 hasAuthorship W3189979155A5043896172 @default.
- W3189979155 hasAuthorship W3189979155A5047932411 @default.
- W3189979155 hasAuthorship W3189979155A5058555426 @default.
- W3189979155 hasAuthorship W3189979155A5064663972 @default.
- W3189979155 hasBestOaLocation W31899791551 @default.
- W3189979155 hasConcept C108583219 @default.
- W3189979155 hasConcept C119857082 @default.
- W3189979155 hasConcept C132525143 @default.
- W3189979155 hasConcept C154945302 @default.
- W3189979155 hasConcept C162324750 @default.
- W3189979155 hasConcept C187736073 @default.
- W3189979155 hasConcept C2776436953 @default.
- W3189979155 hasConcept C2778827112 @default.
- W3189979155 hasConcept C2780451532 @default.
- W3189979155 hasConcept C41008148 @default.
- W3189979155 hasConcept C80444323 @default.
- W3189979155 hasConceptScore W3189979155C108583219 @default.
- W3189979155 hasConceptScore W3189979155C119857082 @default.
- W3189979155 hasConceptScore W3189979155C132525143 @default.
- W3189979155 hasConceptScore W3189979155C154945302 @default.
- W3189979155 hasConceptScore W3189979155C162324750 @default.
- W3189979155 hasConceptScore W3189979155C187736073 @default.
- W3189979155 hasConceptScore W3189979155C2776436953 @default.
- W3189979155 hasConceptScore W3189979155C2778827112 @default.
- W3189979155 hasConceptScore W3189979155C2780451532 @default.
- W3189979155 hasConceptScore W3189979155C41008148 @default.
- W3189979155 hasConceptScore W3189979155C80444323 @default.
- W3189979155 hasLocation W31899791551 @default.
- W3189979155 hasOpenAccess W3189979155 @default.
- W3189979155 hasPrimaryLocation W31899791551 @default.
- W3189979155 hasRelatedWork W2911455822 @default.
- W3189979155 hasRelatedWork W2942650110 @default.
- W3189979155 hasRelatedWork W2961085424 @default.
- W3189979155 hasRelatedWork W2968586400 @default.
- W3189979155 hasRelatedWork W3021430260 @default.
- W3189979155 hasRelatedWork W3160244858 @default.
- W3189979155 hasRelatedWork W3200179079 @default.
- W3189979155 hasRelatedWork W4281986673 @default.
- W3189979155 hasRelatedWork W4309938360 @default.
- W3189979155 hasRelatedWork W4362613237 @default.
- W3189979155 isParatext "false" @default.
- W3189979155 isRetracted "false" @default.
- W3189979155 magId "3189979155" @default.
- W3189979155 workType "article" @default.