Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308121148> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4308121148 endingPage "3574" @default.
- W4308121148 startingPage "3574" @default.
- W4308121148 abstract "The posting of offensive content in regional languages has increased as a result of the accessibility of low-cost internet and the widespread use of online social media. Despite the large number of comments available online, only a small percentage of them are offensive, resulting in an unequal distribution of offensive and non-offensive comments. Due to this class imbalance, classifiers may be biased toward the class with the most samples, i.e., the non-offensive class. To address class imbalance, a Multilingual Translation-based Data augmentation technique for Offensive content identification in Tamil text data (MTDOT) is proposed in this work. The proposed MTDOT method is applied to HASOC’21, which is the Tamil offensive content dataset. To obtain a balanced dataset, each offensive comment is augmented using multi-level back translation with English and Malayalam as intermediate languages. Another balanced dataset is generated by employing single-level back translation with Malayalam, Kannada, and Telugu as intermediate languages. While both approaches are equally effective, the proposed multi-level back-translation data augmentation approach produces more diverse data, which is evident from the BLEU score. The MTDOT technique proposed in this work achieved a promising improvement in F1-score over the widely used SMOTE class balancing method by 65%." @default.
- W4308121148 created "2022-11-08" @default.
- W4308121148 creator A5024315951 @default.
- W4308121148 creator A5082729994 @default.
- W4308121148 date "2022-11-01" @default.
- W4308121148 modified "2023-10-02" @default.
- W4308121148 title "MTDOT: A Multilingual Translation-Based Data Augmentation Technique for Offensive Content Identification in Tamil Text Data" @default.
- W4308121148 cites W1496056137 @default.
- W4308121148 cites W2091007025 @default.
- W4308121148 cites W2132791018 @default.
- W4308121148 cites W2148143831 @default.
- W4308121148 cites W2338318698 @default.
- W4308121148 cites W2963216553 @default.
- W4308121148 cites W3176923149 @default.
- W4308121148 cites W4210579724 @default.
- W4308121148 cites W4280589882 @default.
- W4308121148 cites W4285268112 @default.
- W4308121148 doi "https://doi.org/10.3390/electronics11213574" @default.
- W4308121148 hasPublicationYear "2022" @default.
- W4308121148 type Work @default.
- W4308121148 citedByCount "4" @default.
- W4308121148 countsByYear W43081211482023 @default.
- W4308121148 crossrefType "journal-article" @default.
- W4308121148 hasAuthorship W4308121148A5024315951 @default.
- W4308121148 hasAuthorship W4308121148A5082729994 @default.
- W4308121148 hasBestOaLocation W43081211481 @default.
- W4308121148 hasConcept C116834253 @default.
- W4308121148 hasConcept C119857082 @default.
- W4308121148 hasConcept C138885662 @default.
- W4308121148 hasConcept C140688305 @default.
- W4308121148 hasConcept C154945302 @default.
- W4308121148 hasConcept C176856949 @default.
- W4308121148 hasConcept C204321447 @default.
- W4308121148 hasConcept C2777212361 @default.
- W4308121148 hasConcept C2778756302 @default.
- W4308121148 hasConcept C2779662586 @default.
- W4308121148 hasConcept C28490314 @default.
- W4308121148 hasConcept C33923547 @default.
- W4308121148 hasConcept C41008148 @default.
- W4308121148 hasConcept C41895202 @default.
- W4308121148 hasConcept C42475967 @default.
- W4308121148 hasConcept C59822182 @default.
- W4308121148 hasConcept C86803240 @default.
- W4308121148 hasConceptScore W4308121148C116834253 @default.
- W4308121148 hasConceptScore W4308121148C119857082 @default.
- W4308121148 hasConceptScore W4308121148C138885662 @default.
- W4308121148 hasConceptScore W4308121148C140688305 @default.
- W4308121148 hasConceptScore W4308121148C154945302 @default.
- W4308121148 hasConceptScore W4308121148C176856949 @default.
- W4308121148 hasConceptScore W4308121148C204321447 @default.
- W4308121148 hasConceptScore W4308121148C2777212361 @default.
- W4308121148 hasConceptScore W4308121148C2778756302 @default.
- W4308121148 hasConceptScore W4308121148C2779662586 @default.
- W4308121148 hasConceptScore W4308121148C28490314 @default.
- W4308121148 hasConceptScore W4308121148C33923547 @default.
- W4308121148 hasConceptScore W4308121148C41008148 @default.
- W4308121148 hasConceptScore W4308121148C41895202 @default.
- W4308121148 hasConceptScore W4308121148C42475967 @default.
- W4308121148 hasConceptScore W4308121148C59822182 @default.
- W4308121148 hasConceptScore W4308121148C86803240 @default.
- W4308121148 hasIssue "21" @default.
- W4308121148 hasLocation W43081211481 @default.
- W4308121148 hasOpenAccess W4308121148 @default.
- W4308121148 hasPrimaryLocation W43081211481 @default.
- W4308121148 hasRelatedWork W2015787804 @default.
- W4308121148 hasRelatedWork W3152688761 @default.
- W4308121148 hasRelatedWork W3214215545 @default.
- W4308121148 hasRelatedWork W379929139 @default.
- W4308121148 hasRelatedWork W400493711 @default.
- W4308121148 hasRelatedWork W4286859220 @default.
- W4308121148 hasRelatedWork W4293229170 @default.
- W4308121148 hasRelatedWork W565111942 @default.
- W4308121148 hasRelatedWork W586237208 @default.
- W4308121148 hasRelatedWork W654102581 @default.
- W4308121148 hasVolume "11" @default.
- W4308121148 isParatext "false" @default.
- W4308121148 isRetracted "false" @default.
- W4308121148 workType "article" @default.