Matches in SemOpenAlex for { <https://semopenalex.org/work/W3156955725> ?p ?o ?g. }
- W3156955725 endingPage "127" @default.
- W3156955725 startingPage "120" @default.
- W3156955725 abstract "This paper describes the submissions by team HWR to the Dravidian Language Identification (DLI) shared task organized at VarDial 2021 workshop. The DLI training set includes 16,674 YouTube comments written in Roman script containing code-mixed text with English and one of the three South Dravidian languages: Kannada, Malayalam, and Tamil. We submitted results generated using two models, a Naive Bayes classifier with adaptive language models, which has shown to obtain competitive performance in many language and dialect identification tasks, and a transformer-based model which is widely regarded as the state-of-the-art in a number of NLP tasks. Our first submission was sent in the closed submission track using only the training set provided by the shared task organisers, whereas the second submission is considered to be open as it used a pretrained model trained with external data. Our team attained shared second position in the shared task with the submission based on Naive Bayes. Our results reinforce the idea that deep learning methods are not as competitive in language identification related tasks as they are in many other text classification tasks." @default.
- W3156955725 created "2021-04-26" @default.
- W3156955725 creator A5024937008 @default.
- W3156955725 creator A5030132131 @default.
- W3156955725 creator A5061000186 @default.
- W3156955725 date "2021-04-01" @default.
- W3156955725 modified "2023-10-01" @default.
- W3156955725 title "Comparing Approaches to Dravidian Language Identification" @default.
- W3156955725 cites W1546539812 @default.
- W3156955725 cites W1572771042 @default.
- W3156955725 cites W1791088224 @default.
- W3156955725 cites W2051461667 @default.
- W3156955725 cites W2068130800 @default.
- W3156955725 cites W2081748579 @default.
- W3156955725 cites W2181624922 @default.
- W3156955725 cites W244375653 @default.
- W3156955725 cites W2527936838 @default.
- W3156955725 cites W2583190795 @default.
- W3156955725 cites W2626499725 @default.
- W3156955725 cites W2740300618 @default.
- W3156955725 cites W2741135879 @default.
- W3156955725 cites W2899166839 @default.
- W3156955725 cites W2914870929 @default.
- W3156955725 cites W2962270437 @default.
- W3156955725 cites W2962937786 @default.
- W3156955725 cites W2963341956 @default.
- W3156955725 cites W2964842416 @default.
- W3156955725 cites W2975529437 @default.
- W3156955725 cites W2983040767 @default.
- W3156955725 cites W2986670477 @default.
- W3156955725 cites W3004178028 @default.
- W3156955725 cites W3030198970 @default.
- W3156955725 cites W3030409819 @default.
- W3156955725 cites W3032261270 @default.
- W3156955725 cites W3032739230 @default.
- W3156955725 cites W3088333221 @default.
- W3156955725 cites W3100941475 @default.
- W3156955725 cites W3109540321 @default.
- W3156955725 cites W3114626748 @default.
- W3156955725 cites W3115583443 @default.
- W3156955725 cites W3115906794 @default.
- W3156955725 cites W3119228675 @default.
- W3156955725 cites W3120163718 @default.
- W3156955725 cites W3144290041 @default.
- W3156955725 cites W3156548412 @default.
- W3156955725 cites W3170547996 @default.
- W3156955725 cites W319622301 @default.
- W3156955725 cites W402546610 @default.
- W3156955725 cites W851785710 @default.
- W3156955725 hasPublicationYear "2021" @default.
- W3156955725 type Work @default.
- W3156955725 sameAs 3156955725 @default.
- W3156955725 citedByCount "9" @default.
- W3156955725 countsByYear W31569557252021 @default.
- W3156955725 countsByYear W31569557252023 @default.
- W3156955725 crossrefType "journal-article" @default.
- W3156955725 hasAuthorship W3156955725A5024937008 @default.
- W3156955725 hasAuthorship W3156955725A5030132131 @default.
- W3156955725 hasAuthorship W3156955725A5061000186 @default.
- W3156955725 hasConcept C116834253 @default.
- W3156955725 hasConcept C12267149 @default.
- W3156955725 hasConcept C127413603 @default.
- W3156955725 hasConcept C129792486 @default.
- W3156955725 hasConcept C137293760 @default.
- W3156955725 hasConcept C138885662 @default.
- W3156955725 hasConcept C140688305 @default.
- W3156955725 hasConcept C154945302 @default.
- W3156955725 hasConcept C195324797 @default.
- W3156955725 hasConcept C201995342 @default.
- W3156955725 hasConcept C203005215 @default.
- W3156955725 hasConcept C204321447 @default.
- W3156955725 hasConcept C2779662586 @default.
- W3156955725 hasConcept C2780451532 @default.
- W3156955725 hasConcept C41008148 @default.
- W3156955725 hasConcept C41895202 @default.
- W3156955725 hasConcept C52001869 @default.
- W3156955725 hasConcept C59822182 @default.
- W3156955725 hasConcept C86803240 @default.
- W3156955725 hasConcept C95623464 @default.
- W3156955725 hasConceptScore W3156955725C116834253 @default.
- W3156955725 hasConceptScore W3156955725C12267149 @default.
- W3156955725 hasConceptScore W3156955725C127413603 @default.
- W3156955725 hasConceptScore W3156955725C129792486 @default.
- W3156955725 hasConceptScore W3156955725C137293760 @default.
- W3156955725 hasConceptScore W3156955725C138885662 @default.
- W3156955725 hasConceptScore W3156955725C140688305 @default.
- W3156955725 hasConceptScore W3156955725C154945302 @default.
- W3156955725 hasConceptScore W3156955725C195324797 @default.
- W3156955725 hasConceptScore W3156955725C201995342 @default.
- W3156955725 hasConceptScore W3156955725C203005215 @default.
- W3156955725 hasConceptScore W3156955725C204321447 @default.
- W3156955725 hasConceptScore W3156955725C2779662586 @default.
- W3156955725 hasConceptScore W3156955725C2780451532 @default.
- W3156955725 hasConceptScore W3156955725C41008148 @default.
- W3156955725 hasConceptScore W3156955725C41895202 @default.
- W3156955725 hasConceptScore W3156955725C52001869 @default.
- W3156955725 hasConceptScore W3156955725C59822182 @default.
- W3156955725 hasConceptScore W3156955725C86803240 @default.