Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571949> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4385571949 abstract "This paper describes SinaAI’s participation in SemEval-2023 Task 3, which involves detecting propaganda in news articles across multiple languages. The task comprises three sub-tasks: (i) genre detection, (ii) news framing,and (iii) persuasion technique identification.The employed dataset includes news articles in nine languages and domains, including English, French, Italian, German, Polish, Russian, Georgian, Greek, and Spanish, with labeled instances of news framing, genre, and persuasion techniques. Our approach combines fine-tuning multilingual language models such as XLM, LaBSE, and mBERT with data augmentation techniques. Our experimental results show that XLM outperforms other models in terms of F1-Micro in and F1-Macro, and the ensemble of XLM and LaBSE achieved the best performance. Our study highlights the effectiveness of multilingual sentence embedding models in multilingual propaganda detection. Our models achieved highest score for two languages (greek and italy) in sub-task 1 and one language (Russian) for sub-task 2." @default.
- W4385571949 created "2023-08-05" @default.
- W4385571949 creator A5014316659 @default.
- W4385571949 creator A5043520995 @default.
- W4385571949 creator A5087261980 @default.
- W4385571949 creator A5087638476 @default.
- W4385571949 creator A5092596315 @default.
- W4385571949 creator A5092596316 @default.
- W4385571949 date "2023-01-01" @default.
- W4385571949 modified "2023-09-25" @default.
- W4385571949 title "SinaAI at SemEval-2023 Task 3: A Multilingual Transformer Language Model-based Approach for the Detection of News Genre, Framing and Persuasion Techniques" @default.
- W4385571949 doi "https://doi.org/10.18653/v1/2023.semeval-1.300" @default.
- W4385571949 hasPublicationYear "2023" @default.
- W4385571949 type Work @default.
- W4385571949 citedByCount "0" @default.
- W4385571949 crossrefType "proceedings-article" @default.
- W4385571949 hasAuthorship W4385571949A5014316659 @default.
- W4385571949 hasAuthorship W4385571949A5043520995 @default.
- W4385571949 hasAuthorship W4385571949A5087261980 @default.
- W4385571949 hasAuthorship W4385571949A5087638476 @default.
- W4385571949 hasAuthorship W4385571949A5092596315 @default.
- W4385571949 hasAuthorship W4385571949A5092596316 @default.
- W4385571949 hasBestOaLocation W43855719491 @default.
- W4385571949 hasConcept C121332964 @default.
- W4385571949 hasConcept C137293760 @default.
- W4385571949 hasConcept C138885662 @default.
- W4385571949 hasConcept C154945302 @default.
- W4385571949 hasConcept C162324750 @default.
- W4385571949 hasConcept C165801399 @default.
- W4385571949 hasConcept C166957645 @default.
- W4385571949 hasConcept C169087156 @default.
- W4385571949 hasConcept C187736073 @default.
- W4385571949 hasConcept C204321447 @default.
- W4385571949 hasConcept C2777530160 @default.
- W4385571949 hasConcept C2780451532 @default.
- W4385571949 hasConcept C2781310500 @default.
- W4385571949 hasConcept C41008148 @default.
- W4385571949 hasConcept C41895202 @default.
- W4385571949 hasConcept C44572571 @default.
- W4385571949 hasConcept C62520636 @default.
- W4385571949 hasConcept C66322947 @default.
- W4385571949 hasConcept C95457728 @default.
- W4385571949 hasConceptScore W4385571949C121332964 @default.
- W4385571949 hasConceptScore W4385571949C137293760 @default.
- W4385571949 hasConceptScore W4385571949C138885662 @default.
- W4385571949 hasConceptScore W4385571949C154945302 @default.
- W4385571949 hasConceptScore W4385571949C162324750 @default.
- W4385571949 hasConceptScore W4385571949C165801399 @default.
- W4385571949 hasConceptScore W4385571949C166957645 @default.
- W4385571949 hasConceptScore W4385571949C169087156 @default.
- W4385571949 hasConceptScore W4385571949C187736073 @default.
- W4385571949 hasConceptScore W4385571949C204321447 @default.
- W4385571949 hasConceptScore W4385571949C2777530160 @default.
- W4385571949 hasConceptScore W4385571949C2780451532 @default.
- W4385571949 hasConceptScore W4385571949C2781310500 @default.
- W4385571949 hasConceptScore W4385571949C41008148 @default.
- W4385571949 hasConceptScore W4385571949C41895202 @default.
- W4385571949 hasConceptScore W4385571949C44572571 @default.
- W4385571949 hasConceptScore W4385571949C62520636 @default.
- W4385571949 hasConceptScore W4385571949C66322947 @default.
- W4385571949 hasConceptScore W4385571949C95457728 @default.
- W4385571949 hasLocation W43855719491 @default.
- W4385571949 hasOpenAccess W4385571949 @default.
- W4385571949 hasPrimaryLocation W43855719491 @default.
- W4385571949 hasRelatedWork W2128514324 @default.
- W4385571949 hasRelatedWork W2465261327 @default.
- W4385571949 hasRelatedWork W2937421192 @default.
- W4385571949 hasRelatedWork W2949737549 @default.
- W4385571949 hasRelatedWork W3082447286 @default.
- W4385571949 hasRelatedWork W3109777806 @default.
- W4385571949 hasRelatedWork W3184514313 @default.
- W4385571949 hasRelatedWork W3186577291 @default.
- W4385571949 hasRelatedWork W4313680752 @default.
- W4385571949 hasRelatedWork W95183648 @default.
- W4385571949 isParatext "false" @default.
- W4385571949 isRetracted "false" @default.
- W4385571949 workType "article" @default.