Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208746721> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3208746721 abstract "Most existing approaches to script event prediction rely on manually labeled data heavily, which is often expensive to obtain. To cope with the training data bottleneck, we investigate methods of combining multiple self-supervised tasks, i.e. tasks where models are explicitly trained with automatically generated labels. We propose two self-supervised pre-training tasks:one is End Identification and the other is Contrastive Scoring. Multi-task learning framework is then leveraged to combine these two tasks to jointly train the model. The pre-trained model is then fine-tuned using human-annotated script event prediction training data. Experimental results on the commonly used dataset show that our approach can achieve competitive performance compared to the previous models which are trained with the whole dataset by using just 10% of the training data, and our model trained on the whole dataset outperforms previous models significantly." @default.
- W3208746721 created "2021-11-08" @default.
- W3208746721 creator A5004171626 @default.
- W3208746721 creator A5045570568 @default.
- W3208746721 creator A5071321132 @default.
- W3208746721 creator A5076858450 @default.
- W3208746721 creator A5079010450 @default.
- W3208746721 creator A5084360986 @default.
- W3208746721 creator A5086155499 @default.
- W3208746721 date "2021-10-26" @default.
- W3208746721 modified "2023-09-27" @default.
- W3208746721 title "Multi-Task Self-Supervised Learning for Script Event Prediction" @default.
- W3208746721 cites W2758362814 @default.
- W3208746721 cites W2804547589 @default.
- W3208746721 cites W2904617336 @default.
- W3208746721 cites W2952750383 @default.
- W3208746721 cites W2963826423 @default.
- W3208746721 cites W2970453125 @default.
- W3208746721 cites W2996888978 @default.
- W3208746721 cites W2998704965 @default.
- W3208746721 cites W3118202953 @default.
- W3208746721 cites W343636949 @default.
- W3208746721 doi "https://doi.org/10.1145/3459637.3482150" @default.
- W3208746721 hasPublicationYear "2021" @default.
- W3208746721 type Work @default.
- W3208746721 sameAs 3208746721 @default.
- W3208746721 citedByCount "1" @default.
- W3208746721 countsByYear W32087467212023 @default.
- W3208746721 crossrefType "proceedings-article" @default.
- W3208746721 hasAuthorship W3208746721A5004171626 @default.
- W3208746721 hasAuthorship W3208746721A5045570568 @default.
- W3208746721 hasAuthorship W3208746721A5071321132 @default.
- W3208746721 hasAuthorship W3208746721A5076858450 @default.
- W3208746721 hasAuthorship W3208746721A5079010450 @default.
- W3208746721 hasAuthorship W3208746721A5084360986 @default.
- W3208746721 hasAuthorship W3208746721A5086155499 @default.
- W3208746721 hasConcept C116834253 @default.
- W3208746721 hasConcept C119857082 @default.
- W3208746721 hasConcept C121332964 @default.
- W3208746721 hasConcept C149635348 @default.
- W3208746721 hasConcept C154945302 @default.
- W3208746721 hasConcept C162324750 @default.
- W3208746721 hasConcept C187736073 @default.
- W3208746721 hasConcept C204321447 @default.
- W3208746721 hasConcept C2776145971 @default.
- W3208746721 hasConcept C2779662365 @default.
- W3208746721 hasConcept C2780451532 @default.
- W3208746721 hasConcept C2780513914 @default.
- W3208746721 hasConcept C41008148 @default.
- W3208746721 hasConcept C59822182 @default.
- W3208746721 hasConcept C62520636 @default.
- W3208746721 hasConcept C86803240 @default.
- W3208746721 hasConceptScore W3208746721C116834253 @default.
- W3208746721 hasConceptScore W3208746721C119857082 @default.
- W3208746721 hasConceptScore W3208746721C121332964 @default.
- W3208746721 hasConceptScore W3208746721C149635348 @default.
- W3208746721 hasConceptScore W3208746721C154945302 @default.
- W3208746721 hasConceptScore W3208746721C162324750 @default.
- W3208746721 hasConceptScore W3208746721C187736073 @default.
- W3208746721 hasConceptScore W3208746721C204321447 @default.
- W3208746721 hasConceptScore W3208746721C2776145971 @default.
- W3208746721 hasConceptScore W3208746721C2779662365 @default.
- W3208746721 hasConceptScore W3208746721C2780451532 @default.
- W3208746721 hasConceptScore W3208746721C2780513914 @default.
- W3208746721 hasConceptScore W3208746721C41008148 @default.
- W3208746721 hasConceptScore W3208746721C59822182 @default.
- W3208746721 hasConceptScore W3208746721C62520636 @default.
- W3208746721 hasConceptScore W3208746721C86803240 @default.
- W3208746721 hasFunder F4320321001 @default.
- W3208746721 hasFunder F4320335777 @default.
- W3208746721 hasLocation W32087467211 @default.
- W3208746721 hasOpenAccess W3208746721 @default.
- W3208746721 hasPrimaryLocation W32087467211 @default.
- W3208746721 hasRelatedWork W2081647779 @default.
- W3208746721 hasRelatedWork W2752124967 @default.
- W3208746721 hasRelatedWork W2761417937 @default.
- W3208746721 hasRelatedWork W2970232715 @default.
- W3208746721 hasRelatedWork W3003030048 @default.
- W3208746721 hasRelatedWork W3081459453 @default.
- W3208746721 hasRelatedWork W3120027560 @default.
- W3208746721 hasRelatedWork W3184435227 @default.
- W3208746721 hasRelatedWork W3185852197 @default.
- W3208746721 hasRelatedWork W4313071293 @default.
- W3208746721 isParatext "false" @default.
- W3208746721 isRetracted "false" @default.
- W3208746721 magId "3208746721" @default.
- W3208746721 workType "article" @default.