Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892525833> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2892525833 endingPage "121" @default.
- W2892525833 startingPage "106" @default.
- W2892525833 abstract "Standard approaches to named entity recognition (NER) are based on sequential labeling methods, such as conditional random fields (CRFs), which label each word in a sentence and extract entities from them that correspond to named entities. With the extensive deployment of deep learning methods for sequential labeling tasks, state-of-the-art NER performance has been achieved on long short-term memory (LSTM) architectures using only basic features. In this paper, we address Korean NER tasks and propose an extension of a bidirectional LSTM CRF by investigating character-based representation. Our extension involves deploying a hybrid representation using ConvNet and LSTM for the sequential modeling of characters, namely a character-based LSTM-ConvNet hybrid representation. Using morphemes as processing units for bidirectional LSTM, we apply a proposed hybrid representation composed of morpheme vectors. Experimental results showed that the proposed LSTM-ConvNet hybrid representation yielded improvements over each single representation on standard Korean NER tasks." @default.
- W2892525833 created "2018-10-05" @default.
- W2892525833 creator A5007596776 @default.
- W2892525833 creator A5010247077 @default.
- W2892525833 creator A5033091196 @default.
- W2892525833 creator A5066848156 @default.
- W2892525833 date "2019-03-01" @default.
- W2892525833 modified "2023-10-16" @default.
- W2892525833 title "Improving LSTM CRFs using character-based compositions for Korean named entity recognition" @default.
- W2892525833 cites W1447868166 @default.
- W2892525833 cites W2913389685 @default.
- W2892525833 cites W2963625095 @default.
- W2892525833 cites W4231109964 @default.
- W2892525833 doi "https://doi.org/10.1016/j.csl.2018.09.005" @default.
- W2892525833 hasPublicationYear "2019" @default.
- W2892525833 type Work @default.
- W2892525833 sameAs 2892525833 @default.
- W2892525833 citedByCount "22" @default.
- W2892525833 countsByYear W28925258332019 @default.
- W2892525833 countsByYear W28925258332020 @default.
- W2892525833 countsByYear W28925258332021 @default.
- W2892525833 countsByYear W28925258332022 @default.
- W2892525833 countsByYear W28925258332023 @default.
- W2892525833 crossrefType "journal-article" @default.
- W2892525833 hasAuthorship W2892525833A5007596776 @default.
- W2892525833 hasAuthorship W2892525833A5010247077 @default.
- W2892525833 hasAuthorship W2892525833A5033091196 @default.
- W2892525833 hasAuthorship W2892525833A5066848156 @default.
- W2892525833 hasConcept C152565575 @default.
- W2892525833 hasConcept C153180895 @default.
- W2892525833 hasConcept C154945302 @default.
- W2892525833 hasConcept C162324750 @default.
- W2892525833 hasConcept C165297611 @default.
- W2892525833 hasConcept C17744445 @default.
- W2892525833 hasConcept C187736073 @default.
- W2892525833 hasConcept C199539241 @default.
- W2892525833 hasConcept C204321447 @default.
- W2892525833 hasConcept C2524010 @default.
- W2892525833 hasConcept C2775953691 @default.
- W2892525833 hasConcept C2776359362 @default.
- W2892525833 hasConcept C2777530160 @default.
- W2892525833 hasConcept C2779135771 @default.
- W2892525833 hasConcept C2780451532 @default.
- W2892525833 hasConcept C2780861071 @default.
- W2892525833 hasConcept C28490314 @default.
- W2892525833 hasConcept C33923547 @default.
- W2892525833 hasConcept C35639132 @default.
- W2892525833 hasConcept C41008148 @default.
- W2892525833 hasConcept C94625758 @default.
- W2892525833 hasConceptScore W2892525833C152565575 @default.
- W2892525833 hasConceptScore W2892525833C153180895 @default.
- W2892525833 hasConceptScore W2892525833C154945302 @default.
- W2892525833 hasConceptScore W2892525833C162324750 @default.
- W2892525833 hasConceptScore W2892525833C165297611 @default.
- W2892525833 hasConceptScore W2892525833C17744445 @default.
- W2892525833 hasConceptScore W2892525833C187736073 @default.
- W2892525833 hasConceptScore W2892525833C199539241 @default.
- W2892525833 hasConceptScore W2892525833C204321447 @default.
- W2892525833 hasConceptScore W2892525833C2524010 @default.
- W2892525833 hasConceptScore W2892525833C2775953691 @default.
- W2892525833 hasConceptScore W2892525833C2776359362 @default.
- W2892525833 hasConceptScore W2892525833C2777530160 @default.
- W2892525833 hasConceptScore W2892525833C2779135771 @default.
- W2892525833 hasConceptScore W2892525833C2780451532 @default.
- W2892525833 hasConceptScore W2892525833C2780861071 @default.
- W2892525833 hasConceptScore W2892525833C28490314 @default.
- W2892525833 hasConceptScore W2892525833C33923547 @default.
- W2892525833 hasConceptScore W2892525833C35639132 @default.
- W2892525833 hasConceptScore W2892525833C41008148 @default.
- W2892525833 hasConceptScore W2892525833C94625758 @default.
- W2892525833 hasLocation W28925258331 @default.
- W2892525833 hasOpenAccess W2892525833 @default.
- W2892525833 hasPrimaryLocation W28925258331 @default.
- W2892525833 hasRelatedWork W189110383 @default.
- W2892525833 hasRelatedWork W1964783010 @default.
- W2892525833 hasRelatedWork W2027233318 @default.
- W2892525833 hasRelatedWork W2062502130 @default.
- W2892525833 hasRelatedWork W2132038179 @default.
- W2892525833 hasRelatedWork W2399696375 @default.
- W2892525833 hasRelatedWork W2798423868 @default.
- W2892525833 hasRelatedWork W2962906565 @default.
- W2892525833 hasRelatedWork W2964160000 @default.
- W2892525833 hasRelatedWork W4250494529 @default.
- W2892525833 hasVolume "54" @default.
- W2892525833 isParatext "false" @default.
- W2892525833 isRetracted "false" @default.
- W2892525833 magId "2892525833" @default.
- W2892525833 workType "article" @default.