Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571185> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4385571185 abstract "Despite the rapid development of neural-based models, syntax still plays a crucial role in modern natural language processing. However, few studies have incorporated syntactic information into ancient Chinese understanding tasks due to the lack of syntactic annotation. This paper explores the role of syntax in ancient Chinese understanding based on the noisy syntax trees from unsupervised derivation and modern Chinese syntax parsers. On top of that, we propose a novel syntax encoding component – confidence-based syntax encoding network (cSEN) to alleviate the side effects from the existing noise caused by unsupervised syntax derivation and the incompatibility between ancient and modern Chinese. Experiments on two typical ancient Chinese understanding tasks, ancient poetry theme classification and ancient-modern Chinese translation, demonstrate that syntactic information can effectively enhance the understanding of ancient Chinese over strong baselines, and that the proposed cSEN plays an important role in noisy scenarios." @default.
- W4385571185 created "2023-08-05" @default.
- W4385571185 creator A5002584135 @default.
- W4385571185 creator A5015542553 @default.
- W4385571185 creator A5020622531 @default.
- W4385571185 creator A5074052405 @default.
- W4385571185 date "2023-01-01" @default.
- W4385571185 modified "2023-09-24" @default.
- W4385571185 title "Enhancing Ancient Chinese Understanding with Derived Noisy Syntax Trees" @default.
- W4385571185 doi "https://doi.org/10.18653/v1/2023.acl-srw.15" @default.
- W4385571185 hasPublicationYear "2023" @default.
- W4385571185 type Work @default.
- W4385571185 citedByCount "0" @default.
- W4385571185 crossrefType "proceedings-article" @default.
- W4385571185 hasAuthorship W4385571185A5002584135 @default.
- W4385571185 hasAuthorship W4385571185A5015542553 @default.
- W4385571185 hasAuthorship W4385571185A5020622531 @default.
- W4385571185 hasAuthorship W4385571185A5074052405 @default.
- W4385571185 hasBestOaLocation W43855711851 @default.
- W4385571185 hasConcept C114408938 @default.
- W4385571185 hasConcept C125411270 @default.
- W4385571185 hasConcept C138885662 @default.
- W4385571185 hasConcept C154945302 @default.
- W4385571185 hasConcept C186644900 @default.
- W4385571185 hasConcept C204321447 @default.
- W4385571185 hasConcept C41008148 @default.
- W4385571185 hasConcept C41895202 @default.
- W4385571185 hasConcept C58646249 @default.
- W4385571185 hasConcept C60048249 @default.
- W4385571185 hasConceptScore W4385571185C114408938 @default.
- W4385571185 hasConceptScore W4385571185C125411270 @default.
- W4385571185 hasConceptScore W4385571185C138885662 @default.
- W4385571185 hasConceptScore W4385571185C154945302 @default.
- W4385571185 hasConceptScore W4385571185C186644900 @default.
- W4385571185 hasConceptScore W4385571185C204321447 @default.
- W4385571185 hasConceptScore W4385571185C41008148 @default.
- W4385571185 hasConceptScore W4385571185C41895202 @default.
- W4385571185 hasConceptScore W4385571185C58646249 @default.
- W4385571185 hasConceptScore W4385571185C60048249 @default.
- W4385571185 hasLocation W43855711851 @default.
- W4385571185 hasOpenAccess W4385571185 @default.
- W4385571185 hasPrimaryLocation W43855711851 @default.
- W4385571185 hasRelatedWork W1972256049 @default.
- W4385571185 hasRelatedWork W2077104824 @default.
- W4385571185 hasRelatedWork W2148321854 @default.
- W4385571185 hasRelatedWork W2159068199 @default.
- W4385571185 hasRelatedWork W2168778844 @default.
- W4385571185 hasRelatedWork W2393678839 @default.
- W4385571185 hasRelatedWork W2483803551 @default.
- W4385571185 hasRelatedWork W2765354873 @default.
- W4385571185 hasRelatedWork W4254390385 @default.
- W4385571185 hasRelatedWork W850463266 @default.
- W4385571185 isParatext "false" @default.
- W4385571185 isRetracted "false" @default.
- W4385571185 workType "article" @default.