FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950333634> ?p ?o ?g. }

• W2950333634 abstract "Morphological tagging is challenging for morphologically rich languages due to the large target space and the need for more training data to minimize model sparsity. Dialectal variants of morphologically rich languages suffer more as they tend to be more noisy and have less resources. In this paper we explore the use of multitask learning and adversarial training to address morphological richness and dialectal variations in the context of full morphological tagging. We use multitask learning for joint morphological modeling for the features within two dialects, and as a knowledge-transfer scheme for cross-dialectal modeling. We use adversarial training to learn dialect invariant features that can help the knowledge-transfer scheme from the high to low-resource variants. We work with two dialectal variants: Modern Standard Arabic (high-resource “dialect’”) and Egyptian Arabic (low-resource dialect) as a case study. Our models achieve state-of-the-art results for both. Furthermore, adversarial training provides more significant improvement when using smaller training datasets in particular." @default.
• W2950333634 created "2019-06-27" @default.
• W2950333634 creator A5084517393 @default.
• W2950333634 creator A5089887413 @default.
• W2950333634 date "2019-01-01" @default.
• W2950333634 modified "2023-09-23" @default.
• W2950333634 title "Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling" @default.
• W2950333634 cites W131663347 @default.
• W2950333634 cites W137989762 @default.
• W2950333634 cites W1598638450 @default.
• W2950333634 cites W1731081199 @default.
• W2950333634 cites W195406672 @default.
• W2950333634 cites W2004586385 @default.
• W2950333634 cites W2043693083 @default.
• W2950333634 cites W2048978997 @default.
• W2950333634 cites W2099471712 @default.
• W2950333634 cites W2100976324 @default.
• W2950333634 cites W2147272182 @default.
• W2950333634 cites W2153579005 @default.
• W2950333634 cites W2250732891 @default.
• W2950333634 cites W2250741688 @default.
• W2950333634 cites W2347007084 @default.
• W2950333634 cites W2471147443 @default.
• W2950333634 cites W2515098781 @default.
• W2950333634 cites W2516255829 @default.
• W2950333634 cites W2556468274 @default.
• W2950333634 cites W2573043117 @default.
• W2950333634 cites W2575512508 @default.
• W2950333634 cites W2590925815 @default.
• W2950333634 cites W2740144049 @default.
• W2950333634 cites W2757376562 @default.
• W2950333634 cites W2773963565 @default.
• W2950333634 cites W2799060650 @default.
• W2950333634 cites W2804967932 @default.
• W2950333634 cites W2807107081 @default.
• W2950333634 cites W2849265501 @default.
• W2950333634 cites W2890328620 @default.
• W2950333634 cites W2962705709 @default.
• W2950333634 cites W2963826681 @default.
• W2950333634 cites W2963965928 @default.
• W2950333634 cites W2964121744 @default.
• W2950333634 doi "https://doi.org/10.18653/v1/p19-1173" @default.
• W2950333634 hasPublicationYear "2019" @default.
• W2950333634 type Work @default.
• W2950333634 sameAs 2950333634 @default.
• W2950333634 citedByCount "8" @default.
• W2950333634 countsByYear W29503336342019 @default.
• W2950333634 countsByYear W29503336342020 @default.
• W2950333634 countsByYear W29503336342021 @default.
• W2950333634 countsByYear W29503336342022 @default.
• W2950333634 crossrefType "proceedings-article" @default.
• W2950333634 hasAuthorship W2950333634A5084517393 @default.
• W2950333634 hasAuthorship W2950333634A5089887413 @default.
• W2950333634 hasBestOaLocation W29503336341 @default.
• W2950333634 hasConcept C119857082 @default.
• W2950333634 hasConcept C127413603 @default.
• W2950333634 hasConcept C138885662 @default.
• W2950333634 hasConcept C154945302 @default.
• W2950333634 hasConcept C170154142 @default.
• W2950333634 hasConcept C18555067 @default.
• W2950333634 hasConcept C201995342 @default.
• W2950333634 hasConcept C204321447 @default.
• W2950333634 hasConcept C2776401178 @default.
• W2950333634 hasConcept C2780451532 @default.
• W2950333634 hasConcept C28006648 @default.
• W2950333634 hasConcept C37736160 @default.
• W2950333634 hasConcept C41008148 @default.
• W2950333634 hasConcept C41895202 @default.
• W2950333634 hasConcept C59404180 @default.
• W2950333634 hasConceptScore W2950333634C119857082 @default.
• W2950333634 hasConceptScore W2950333634C127413603 @default.
• W2950333634 hasConceptScore W2950333634C138885662 @default.
• W2950333634 hasConceptScore W2950333634C154945302 @default.
• W2950333634 hasConceptScore W2950333634C170154142 @default.
• W2950333634 hasConceptScore W2950333634C18555067 @default.
• W2950333634 hasConceptScore W2950333634C201995342 @default.
• W2950333634 hasConceptScore W2950333634C204321447 @default.
• W2950333634 hasConceptScore W2950333634C2776401178 @default.
• W2950333634 hasConceptScore W2950333634C2780451532 @default.
• W2950333634 hasConceptScore W2950333634C28006648 @default.
• W2950333634 hasConceptScore W2950333634C37736160 @default.
• W2950333634 hasConceptScore W2950333634C41008148 @default.
• W2950333634 hasConceptScore W2950333634C41895202 @default.
• W2950333634 hasConceptScore W2950333634C59404180 @default.
• W2950333634 hasLocation W29503336341 @default.
• W2950333634 hasLocation W29503336342 @default.
• W2950333634 hasOpenAccess W2950333634 @default.
• W2950333634 hasPrimaryLocation W29503336341 @default.
• W2950333634 hasRelatedWork W2165343651 @default.
• W2950333634 hasRelatedWork W2908875379 @default.
• W2950333634 hasRelatedWork W2961085424 @default.
• W2950333634 hasRelatedWork W3037947124 @default.
• W2950333634 hasRelatedWork W3095538999 @default.
• W2950333634 hasRelatedWork W3110006982 @default.
• W2950333634 hasRelatedWork W3200361725 @default.
• W2950333634 hasRelatedWork W4206984194 @default.
• W2950333634 hasRelatedWork W4287750429 @default.
• W2950333634 hasRelatedWork W4288088436 @default.
• W2950333634 isParatext "false" @default.
• W2950333634 isRetracted "false" @default.

• next