Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120788892> ?p ?o ?g. }
- W3120788892 endingPage "225" @default.
- W3120788892 startingPage "215" @default.
- W3120788892 abstract "Globalization has caused the rise of the code-switching phenomenon among multilingual societies. In Arab countries, code-switching between Arabic and English has become frequent, especially through social media platforms. Consequently, research in Natural Language Processing (NLP) systems increased to tackle such a phenomenon. One of the significant challenges of developing code-switched NLP systems is the lack of data itself. In this paper, we propose an open source trained bilingual contextual word embedding models of FLAIR, BERT, and ELECTRA. We also propose a novel contextual word embedding model called KERMIT, which can efficiently map Arabic and English words inside one vector space in terms of data usage. We applied intrinsic and extrinsic evaluation methods to compare the performance of the models. Our results show that FLAIR and FastText achieve the highest results in the sentiment analysis task. However, KERMIT is the best-achieving model on the intrinsic evaluation and named entity recognition. Also, it outperforms the other transformer-based models on question answering task." @default.
- W3120788892 created "2021-01-18" @default.
- W3120788892 creator A5019036487 @default.
- W3120788892 creator A5057373662 @default.
- W3120788892 creator A5080036358 @default.
- W3120788892 date "2020-12-01" @default.
- W3120788892 modified "2023-09-23" @default.
- W3120788892 title "Contextual Embeddings for Arabic-English Code-Switched Data" @default.
- W3120788892 cites W1828724394 @default.
- W3120788892 cites W2014962660 @default.
- W3120788892 cites W2031046474 @default.
- W3120788892 cites W2138923868 @default.
- W3120788892 cites W2142074148 @default.
- W3120788892 cites W2153579005 @default.
- W3120788892 cites W2229725139 @default.
- W3120788892 cites W2250548009 @default.
- W3120788892 cites W2251765408 @default.
- W3120788892 cites W2252212383 @default.
- W3120788892 cites W2471147443 @default.
- W3120788892 cites W2767613622 @default.
- W3120788892 cites W2767784948 @default.
- W3120788892 cites W2798348125 @default.
- W3120788892 cites W2805530518 @default.
- W3120788892 cites W2880875857 @default.
- W3120788892 cites W2891252302 @default.
- W3120788892 cites W2921848514 @default.
- W3120788892 cites W2945896227 @default.
- W3120788892 cites W2946119234 @default.
- W3120788892 cites W2946558277 @default.
- W3120788892 cites W2955603559 @default.
- W3120788892 cites W2962795068 @default.
- W3120788892 cites W2963341956 @default.
- W3120788892 cites W2969143370 @default.
- W3120788892 cites W2970960342 @default.
- W3120788892 cites W2973082572 @default.
- W3120788892 cites W2980282514 @default.
- W3120788892 cites W2982614029 @default.
- W3120788892 cites W2996403597 @default.
- W3120788892 cites W3013571468 @default.
- W3120788892 cites W3088592174 @default.
- W3120788892 cites W3097306574 @default.
- W3120788892 cites W342285082 @default.
- W3120788892 hasPublicationYear "2020" @default.
- W3120788892 type Work @default.
- W3120788892 sameAs 3120788892 @default.
- W3120788892 citedByCount "0" @default.
- W3120788892 crossrefType "journal-article" @default.
- W3120788892 hasAuthorship W3120788892A5019036487 @default.
- W3120788892 hasAuthorship W3120788892A5057373662 @default.
- W3120788892 hasAuthorship W3120788892A5080036358 @default.
- W3120788892 hasConcept C121332964 @default.
- W3120788892 hasConcept C138885662 @default.
- W3120788892 hasConcept C154945302 @default.
- W3120788892 hasConcept C162324750 @default.
- W3120788892 hasConcept C165801399 @default.
- W3120788892 hasConcept C177264268 @default.
- W3120788892 hasConcept C18552078 @default.
- W3120788892 hasConcept C187736073 @default.
- W3120788892 hasConcept C199360897 @default.
- W3120788892 hasConcept C204321447 @default.
- W3120788892 hasConcept C2776760102 @default.
- W3120788892 hasConcept C2777462759 @default.
- W3120788892 hasConcept C2779135771 @default.
- W3120788892 hasConcept C2780451532 @default.
- W3120788892 hasConcept C41008148 @default.
- W3120788892 hasConcept C41608201 @default.
- W3120788892 hasConcept C41895202 @default.
- W3120788892 hasConcept C44291984 @default.
- W3120788892 hasConcept C62520636 @default.
- W3120788892 hasConcept C66322947 @default.
- W3120788892 hasConcept C90805587 @default.
- W3120788892 hasConcept C96455323 @default.
- W3120788892 hasConceptScore W3120788892C121332964 @default.
- W3120788892 hasConceptScore W3120788892C138885662 @default.
- W3120788892 hasConceptScore W3120788892C154945302 @default.
- W3120788892 hasConceptScore W3120788892C162324750 @default.
- W3120788892 hasConceptScore W3120788892C165801399 @default.
- W3120788892 hasConceptScore W3120788892C177264268 @default.
- W3120788892 hasConceptScore W3120788892C18552078 @default.
- W3120788892 hasConceptScore W3120788892C187736073 @default.
- W3120788892 hasConceptScore W3120788892C199360897 @default.
- W3120788892 hasConceptScore W3120788892C204321447 @default.
- W3120788892 hasConceptScore W3120788892C2776760102 @default.
- W3120788892 hasConceptScore W3120788892C2777462759 @default.
- W3120788892 hasConceptScore W3120788892C2779135771 @default.
- W3120788892 hasConceptScore W3120788892C2780451532 @default.
- W3120788892 hasConceptScore W3120788892C41008148 @default.
- W3120788892 hasConceptScore W3120788892C41608201 @default.
- W3120788892 hasConceptScore W3120788892C41895202 @default.
- W3120788892 hasConceptScore W3120788892C44291984 @default.
- W3120788892 hasConceptScore W3120788892C62520636 @default.
- W3120788892 hasConceptScore W3120788892C66322947 @default.
- W3120788892 hasConceptScore W3120788892C90805587 @default.
- W3120788892 hasConceptScore W3120788892C96455323 @default.
- W3120788892 hasLocation W31207888921 @default.
- W3120788892 hasOpenAccess W3120788892 @default.
- W3120788892 hasPrimaryLocation W31207888921 @default.
- W3120788892 hasRelatedWork W1783519389 @default.