Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912807854> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2912807854 abstract "Recently, scholars have demonstrated empirical successes of deep learning in sequence labeling, and most of the prior works focused on the word representation inside the target sentence. Unfortunately, the global information, e.g., domain information of the target document, were ignored in the previous studies. In this paper, we propose an innovative joint learning neural network which can encapsulate the global domain knowledge and the local sentence/token information to enhance the sequence labeling model. Unlike existing studies, the proposed method employs domain labeling output as a latent evidence to facilitate tagging model and such joint embedding information is generated by an enhanced highway network. Meanwhile, a redesigned CRF layer is deployed to bridge the 'local output labels' and 'global domain information'. Various kinds of information can iteratively contribute to each other, and moreover, domain knowledge can be learnt in either supervised or unsupervised environment via the new model. Experiment with multiple data sets shows that the proposed algorithm outperforms classical and most recent state-of-the-art labeling methods." @default.
- W2912807854 created "2019-02-21" @default.
- W2912807854 creator A5081176351 @default.
- W2912807854 creator A5081493266 @default.
- W2912807854 creator A5085665917 @default.
- W2912807854 date "2019-05-13" @default.
- W2912807854 modified "2023-09-27" @default.
- W2912807854 title "Domain-aware Neural Model for Sequence Labeling using Joint Learning" @default.
- W2912807854 cites W1493454437 @default.
- W2912807854 cites W1987458394 @default.
- W2912807854 cites W2019976352 @default.
- W2912807854 cites W2064675550 @default.
- W2912807854 cites W2104518905 @default.
- W2912807854 cites W2125838338 @default.
- W2912807854 cites W2250539671 @default.
- W2912807854 cites W2296283641 @default.
- W2912807854 cites W2604165577 @default.
- W2912807854 cites W2962775474 @default.
- W2912807854 cites W2963563735 @default.
- W2912807854 cites W2963706742 @default.
- W2912807854 cites W3103251639 @default.
- W2912807854 doi "https://doi.org/10.1145/3308558.3313566" @default.
- W2912807854 hasPublicationYear "2019" @default.
- W2912807854 type Work @default.
- W2912807854 sameAs 2912807854 @default.
- W2912807854 citedByCount "0" @default.
- W2912807854 crossrefType "proceedings-article" @default.
- W2912807854 hasAuthorship W2912807854A5081176351 @default.
- W2912807854 hasAuthorship W2912807854A5081493266 @default.
- W2912807854 hasAuthorship W2912807854A5085665917 @default.
- W2912807854 hasConcept C127413603 @default.
- W2912807854 hasConcept C134306372 @default.
- W2912807854 hasConcept C153180895 @default.
- W2912807854 hasConcept C154945302 @default.
- W2912807854 hasConcept C170154142 @default.
- W2912807854 hasConcept C18555067 @default.
- W2912807854 hasConcept C185592680 @default.
- W2912807854 hasConcept C201995342 @default.
- W2912807854 hasConcept C2778112365 @default.
- W2912807854 hasConcept C2780451532 @default.
- W2912807854 hasConcept C33923547 @default.
- W2912807854 hasConcept C35639132 @default.
- W2912807854 hasConcept C36503486 @default.
- W2912807854 hasConcept C41008148 @default.
- W2912807854 hasConcept C55493867 @default.
- W2912807854 hasConceptScore W2912807854C127413603 @default.
- W2912807854 hasConceptScore W2912807854C134306372 @default.
- W2912807854 hasConceptScore W2912807854C153180895 @default.
- W2912807854 hasConceptScore W2912807854C154945302 @default.
- W2912807854 hasConceptScore W2912807854C170154142 @default.
- W2912807854 hasConceptScore W2912807854C18555067 @default.
- W2912807854 hasConceptScore W2912807854C185592680 @default.
- W2912807854 hasConceptScore W2912807854C201995342 @default.
- W2912807854 hasConceptScore W2912807854C2778112365 @default.
- W2912807854 hasConceptScore W2912807854C2780451532 @default.
- W2912807854 hasConceptScore W2912807854C33923547 @default.
- W2912807854 hasConceptScore W2912807854C35639132 @default.
- W2912807854 hasConceptScore W2912807854C36503486 @default.
- W2912807854 hasConceptScore W2912807854C41008148 @default.
- W2912807854 hasConceptScore W2912807854C55493867 @default.
- W2912807854 hasLocation W29128078541 @default.
- W2912807854 hasOpenAccess W2912807854 @default.
- W2912807854 hasPrimaryLocation W29128078541 @default.
- W2912807854 hasRelatedWork W2027246577 @default.
- W2912807854 hasRelatedWork W2030530201 @default.
- W2912807854 hasRelatedWork W2033914206 @default.
- W2912807854 hasRelatedWork W2146076056 @default.
- W2912807854 hasRelatedWork W2163831990 @default.
- W2912807854 hasRelatedWork W2351267244 @default.
- W2912807854 hasRelatedWork W3003836766 @default.
- W2912807854 hasRelatedWork W3011555937 @default.
- W2912807854 hasRelatedWork W3096054746 @default.
- W2912807854 hasRelatedWork W3199858452 @default.
- W2912807854 isParatext "false" @default.
- W2912807854 isRetracted "false" @default.
- W2912807854 magId "2912807854" @default.
- W2912807854 workType "article" @default.