Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362639752> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4362639752 endingPage "13" @default.
- W4362639752 startingPage "1" @default.
- W4362639752 abstract "End-to-end neural network-based approaches have recently demonstrated significant improvements in natural language processing (NLP). However, in the NLP application such as assistant systems, NLP components are still processed to extract results using a pipeline paradigm. The pipeline-based concept has issues with error propagation. In Korean, morphological analysis and part-of-speech (POS) tagging step, incorrectly analyzing POS tags for a sentence containing spacing errors negatively affects other modules behind the POS module. Hence, we present a multi-task learning-based POS tagging neural model for Korean with word spacing challenges. When we apply this model to the Korean morphological analysis and POS tagging, we get findings that are robust to word spacing errors. We adopt syllable-level input and output formats, as well as a simple structure for ELECTRA and RNN-CRF models for multi-task learning, and we achieve a good performance 98.30 of F1, better than previous studies on the Sejong corpus test set." @default.
- W4362639752 created "2023-04-07" @default.
- W4362639752 creator A5009313002 @default.
- W4362639752 creator A5057884782 @default.
- W4362639752 date "2023-06-17" @default.
- W4362639752 modified "2023-09-29" @default.
- W4362639752 title "Robust Multi-task Learning-based Korean POS Tagging to Overcome Word Spacing Errors" @default.
- W4362639752 cites W2031248101 @default.
- W4362639752 cites W2064675550 @default.
- W4362639752 cites W2117130368 @default.
- W4362639752 cites W2118491422 @default.
- W4362639752 cites W2172147831 @default.
- W4362639752 cites W2601779957 @default.
- W4362639752 cites W2913340405 @default.
- W4362639752 cites W2941327948 @default.
- W4362639752 cites W2964234219 @default.
- W4362639752 cites W2971074891 @default.
- W4362639752 cites W3090128560 @default.
- W4362639752 cites W3130868440 @default.
- W4362639752 cites W3163363326 @default.
- W4362639752 cites W4213072039 @default.
- W4362639752 cites W4229365864 @default.
- W4362639752 doi "https://doi.org/10.1145/3591206" @default.
- W4362639752 hasPublicationYear "2023" @default.
- W4362639752 type Work @default.
- W4362639752 citedByCount "0" @default.
- W4362639752 crossrefType "journal-article" @default.
- W4362639752 hasAuthorship W4362639752A5009313002 @default.
- W4362639752 hasAuthorship W4362639752A5057884782 @default.
- W4362639752 hasBestOaLocation W43626397521 @default.
- W4362639752 hasConcept C109089402 @default.
- W4362639752 hasConcept C138885662 @default.
- W4362639752 hasConcept C154945302 @default.
- W4362639752 hasConcept C162324750 @default.
- W4362639752 hasConcept C169903167 @default.
- W4362639752 hasConcept C177264268 @default.
- W4362639752 hasConcept C187736073 @default.
- W4362639752 hasConcept C199360897 @default.
- W4362639752 hasConcept C204321447 @default.
- W4362639752 hasConcept C2777530160 @default.
- W4362639752 hasConcept C2780451532 @default.
- W4362639752 hasConcept C28490314 @default.
- W4362639752 hasConcept C41008148 @default.
- W4362639752 hasConcept C41895202 @default.
- W4362639752 hasConcept C43521106 @default.
- W4362639752 hasConcept C50644808 @default.
- W4362639752 hasConcept C90805587 @default.
- W4362639752 hasConceptScore W4362639752C109089402 @default.
- W4362639752 hasConceptScore W4362639752C138885662 @default.
- W4362639752 hasConceptScore W4362639752C154945302 @default.
- W4362639752 hasConceptScore W4362639752C162324750 @default.
- W4362639752 hasConceptScore W4362639752C169903167 @default.
- W4362639752 hasConceptScore W4362639752C177264268 @default.
- W4362639752 hasConceptScore W4362639752C187736073 @default.
- W4362639752 hasConceptScore W4362639752C199360897 @default.
- W4362639752 hasConceptScore W4362639752C204321447 @default.
- W4362639752 hasConceptScore W4362639752C2777530160 @default.
- W4362639752 hasConceptScore W4362639752C2780451532 @default.
- W4362639752 hasConceptScore W4362639752C28490314 @default.
- W4362639752 hasConceptScore W4362639752C41008148 @default.
- W4362639752 hasConceptScore W4362639752C41895202 @default.
- W4362639752 hasConceptScore W4362639752C43521106 @default.
- W4362639752 hasConceptScore W4362639752C50644808 @default.
- W4362639752 hasConceptScore W4362639752C90805587 @default.
- W4362639752 hasIssue "6" @default.
- W4362639752 hasLocation W43626397521 @default.
- W4362639752 hasOpenAccess W4362639752 @default.
- W4362639752 hasPrimaryLocation W43626397521 @default.
- W4362639752 hasRelatedWork W1539050421 @default.
- W4362639752 hasRelatedWork W1573537589 @default.
- W4362639752 hasRelatedWork W159132833 @default.
- W4362639752 hasRelatedWork W1931781377 @default.
- W4362639752 hasRelatedWork W2015950787 @default.
- W4362639752 hasRelatedWork W2020540721 @default.
- W4362639752 hasRelatedWork W2078268723 @default.
- W4362639752 hasRelatedWork W2125145484 @default.
- W4362639752 hasRelatedWork W2578916128 @default.
- W4362639752 hasRelatedWork W4323066627 @default.
- W4362639752 hasVolume "22" @default.
- W4362639752 isParatext "false" @default.
- W4362639752 isRetracted "false" @default.
- W4362639752 workType "article" @default.