FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890328620> ?p ?o ?g. }

• W2890328620 abstract "Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little exploration in this direction. Both the scarcity of annotated data and the complexity of the language increase the difficulty of the problem. To address these challenges, we use a sequence-to-sequence model with character-based attention, which in addition to its self-learned character embeddings, uses word embeddings pre-trained with an approach that also models subword information. This provides the neural model with access to more linguistic information especially suitable for text normalization, without large parallel corpora. We show that providing the model with word-level features bridges the gap for the neural network approach to achieve a state-of-the-art F1 score on a standard Arabic language correction shared task dataset." @default.
• W2890328620 created "2018-09-27" @default.
• W2890328620 creator A5004503253 @default.
• W2890328620 creator A5084517393 @default.
• W2890328620 creator A5089887413 @default.
• W2890328620 date "2018-01-01" @default.
• W2890328620 modified "2023-10-14" @default.
• W2890328620 title "Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models" @default.
• W2890328620 cites W14596243 @default.
• W2890328620 cites W1902237438 @default.
• W2890328620 cites W2012804051 @default.
• W2890328620 cites W2016589492 @default.
• W2890328620 cites W2064675550 @default.
• W2890328620 cites W2095705004 @default.
• W2890328620 cites W2130942839 @default.
• W2890328620 cites W2147272182 @default.
• W2890328620 cites W2153579005 @default.
• W2890328620 cites W2157331557 @default.
• W2890328620 cites W2250414785 @default.
• W2890328620 cites W2250504723 @default.
• W2890328620 cites W2250751111 @default.
• W2890328620 cites W2251363456 @default.
• W2890328620 cites W2251851155 @default.
• W2890328620 cites W2251944986 @default.
• W2890328620 cites W2321916036 @default.
• W2890328620 cites W2470324779 @default.
• W2890328620 cites W2493916176 @default.
• W2890328620 cites W2757376562 @default.
• W2890328620 cites W2799060650 @default.
• W2890328620 cites W2804967932 @default.
• W2890328620 cites W2893707415 @default.
• W2890328620 cites W2952972707 @default.
• W2890328620 cites W2962739339 @default.
• W2890328620 cites W2963042536 @default.
• W2890328620 cites W2963403868 @default.
• W2890328620 cites W2964121744 @default.
• W2890328620 cites W2964308564 @default.
• W2890328620 cites W3089057597 @default.
• W2890328620 cites W408046128 @default.
• W2890328620 cites W648786980 @default.
• W2890328620 doi "https://doi.org/10.18653/v1/d18-1097" @default.
• W2890328620 hasPublicationYear "2018" @default.
• W2890328620 type Work @default.
• W2890328620 sameAs 2890328620 @default.
• W2890328620 citedByCount "16" @default.
• W2890328620 countsByYear W28903286202019 @default.
• W2890328620 countsByYear W28903286202020 @default.
• W2890328620 countsByYear W28903286202021 @default.
• W2890328620 countsByYear W28903286202022 @default.
• W2890328620 countsByYear W28903286202023 @default.
• W2890328620 crossrefType "proceedings-article" @default.
• W2890328620 hasAuthorship W2890328620A5004503253 @default.
• W2890328620 hasAuthorship W2890328620A5084517393 @default.
• W2890328620 hasAuthorship W2890328620A5089887413 @default.
• W2890328620 hasBestOaLocation W28903286201 @default.
• W2890328620 hasConcept C136886441 @default.
• W2890328620 hasConcept C137293760 @default.
• W2890328620 hasConcept C138885662 @default.
• W2890328620 hasConcept C144024400 @default.
• W2890328620 hasConcept C147168706 @default.
• W2890328620 hasConcept C154945302 @default.
• W2890328620 hasConcept C162324750 @default.
• W2890328620 hasConcept C187736073 @default.
• W2890328620 hasConcept C19165224 @default.
• W2890328620 hasConcept C204321447 @default.
• W2890328620 hasConcept C2524010 @default.
• W2890328620 hasConcept C2778112365 @default.
• W2890328620 hasConcept C2780451532 @default.
• W2890328620 hasConcept C2780861071 @default.
• W2890328620 hasConcept C33923547 @default.
• W2890328620 hasConcept C41008148 @default.
• W2890328620 hasConcept C41895202 @default.
• W2890328620 hasConcept C50644808 @default.
• W2890328620 hasConcept C54355233 @default.
• W2890328620 hasConcept C86803240 @default.
• W2890328620 hasConcept C90805587 @default.
• W2890328620 hasConcept C96455323 @default.
• W2890328620 hasConceptScore W2890328620C136886441 @default.
• W2890328620 hasConceptScore W2890328620C137293760 @default.
• W2890328620 hasConceptScore W2890328620C138885662 @default.
• W2890328620 hasConceptScore W2890328620C144024400 @default.
• W2890328620 hasConceptScore W2890328620C147168706 @default.
• W2890328620 hasConceptScore W2890328620C154945302 @default.
• W2890328620 hasConceptScore W2890328620C162324750 @default.
• W2890328620 hasConceptScore W2890328620C187736073 @default.
• W2890328620 hasConceptScore W2890328620C19165224 @default.
• W2890328620 hasConceptScore W2890328620C204321447 @default.
• W2890328620 hasConceptScore W2890328620C2524010 @default.
• W2890328620 hasConceptScore W2890328620C2778112365 @default.
• W2890328620 hasConceptScore W2890328620C2780451532 @default.
• W2890328620 hasConceptScore W2890328620C2780861071 @default.
• W2890328620 hasConceptScore W2890328620C33923547 @default.
• W2890328620 hasConceptScore W2890328620C41008148 @default.
• W2890328620 hasConceptScore W2890328620C41895202 @default.
• W2890328620 hasConceptScore W2890328620C50644808 @default.
• W2890328620 hasConceptScore W2890328620C54355233 @default.
• W2890328620 hasConceptScore W2890328620C86803240 @default.
• W2890328620 hasConceptScore W2890328620C90805587 @default.
• W2890328620 hasConceptScore W2890328620C96455323 @default.
• W2890328620 hasLocation W28903286201 @default.

• next