Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891632051> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2891632051 endingPage "6601" @default.
- W2891632051 startingPage "6594" @default.
- W2891632051 abstract "Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic compositionality by considering comprehensive syntactic information derived from both the structure and linguistic tags. Specifically, we introduce a structure-aware tag representation constructed by a separate tag-level tree-LSTM. With this, we can control the composition function of the existing wordlevel tree-LSTM by augmenting the representation as a supplementary input to the gate functions of the tree-LSTM. In extensive experiments, we show that models built upon the proposed architecture obtain superior or competitive performance on several sentence-level tasks such as sentiment analysis and natural language inference when compared against previous tree-structured models and other sophisticated neural models." @default.
- W2891632051 created "2018-09-27" @default.
- W2891632051 creator A5004620203 @default.
- W2891632051 creator A5018370260 @default.
- W2891632051 creator A5028120294 @default.
- W2891632051 creator A5039057636 @default.
- W2891632051 creator A5072227362 @default.
- W2891632051 date "2019-07-17" @default.
- W2891632051 modified "2023-09-26" @default.
- W2891632051 title "Dynamic Compositionality in Recursive Neural Networks with Structure-Aware Tag Representations" @default.
- W2891632051 doi "https://doi.org/10.1609/aaai.v33i01.33016594" @default.
- W2891632051 hasPublicationYear "2019" @default.
- W2891632051 type Work @default.
- W2891632051 sameAs 2891632051 @default.
- W2891632051 citedByCount "9" @default.
- W2891632051 countsByYear W28916320512020 @default.
- W2891632051 countsByYear W28916320512021 @default.
- W2891632051 countsByYear W28916320512022 @default.
- W2891632051 crossrefType "journal-article" @default.
- W2891632051 hasAuthorship W2891632051A5004620203 @default.
- W2891632051 hasAuthorship W2891632051A5018370260 @default.
- W2891632051 hasAuthorship W2891632051A5028120294 @default.
- W2891632051 hasAuthorship W2891632051A5039057636 @default.
- W2891632051 hasAuthorship W2891632051A5072227362 @default.
- W2891632051 hasBestOaLocation W28916320511 @default.
- W2891632051 hasConcept C113174947 @default.
- W2891632051 hasConcept C121375916 @default.
- W2891632051 hasConcept C134306372 @default.
- W2891632051 hasConcept C14036430 @default.
- W2891632051 hasConcept C147168706 @default.
- W2891632051 hasConcept C154945302 @default.
- W2891632051 hasConcept C162319229 @default.
- W2891632051 hasConcept C163797641 @default.
- W2891632051 hasConcept C17744445 @default.
- W2891632051 hasConcept C186644900 @default.
- W2891632051 hasConcept C199360897 @default.
- W2891632051 hasConcept C199539241 @default.
- W2891632051 hasConcept C204321447 @default.
- W2891632051 hasConcept C206134035 @default.
- W2891632051 hasConcept C2776214188 @default.
- W2891632051 hasConcept C2776359362 @default.
- W2891632051 hasConcept C2777530160 @default.
- W2891632051 hasConcept C2781466058 @default.
- W2891632051 hasConcept C33923547 @default.
- W2891632051 hasConcept C41008148 @default.
- W2891632051 hasConcept C50644808 @default.
- W2891632051 hasConcept C78458016 @default.
- W2891632051 hasConcept C86803240 @default.
- W2891632051 hasConcept C94625758 @default.
- W2891632051 hasConceptScore W2891632051C113174947 @default.
- W2891632051 hasConceptScore W2891632051C121375916 @default.
- W2891632051 hasConceptScore W2891632051C134306372 @default.
- W2891632051 hasConceptScore W2891632051C14036430 @default.
- W2891632051 hasConceptScore W2891632051C147168706 @default.
- W2891632051 hasConceptScore W2891632051C154945302 @default.
- W2891632051 hasConceptScore W2891632051C162319229 @default.
- W2891632051 hasConceptScore W2891632051C163797641 @default.
- W2891632051 hasConceptScore W2891632051C17744445 @default.
- W2891632051 hasConceptScore W2891632051C186644900 @default.
- W2891632051 hasConceptScore W2891632051C199360897 @default.
- W2891632051 hasConceptScore W2891632051C199539241 @default.
- W2891632051 hasConceptScore W2891632051C204321447 @default.
- W2891632051 hasConceptScore W2891632051C206134035 @default.
- W2891632051 hasConceptScore W2891632051C2776214188 @default.
- W2891632051 hasConceptScore W2891632051C2776359362 @default.
- W2891632051 hasConceptScore W2891632051C2777530160 @default.
- W2891632051 hasConceptScore W2891632051C2781466058 @default.
- W2891632051 hasConceptScore W2891632051C33923547 @default.
- W2891632051 hasConceptScore W2891632051C41008148 @default.
- W2891632051 hasConceptScore W2891632051C50644808 @default.
- W2891632051 hasConceptScore W2891632051C78458016 @default.
- W2891632051 hasConceptScore W2891632051C86803240 @default.
- W2891632051 hasConceptScore W2891632051C94625758 @default.
- W2891632051 hasIssue "01" @default.
- W2891632051 hasLocation W28916320511 @default.
- W2891632051 hasLocation W28916320512 @default.
- W2891632051 hasOpenAccess W2891632051 @default.
- W2891632051 hasPrimaryLocation W28916320511 @default.
- W2891632051 hasRelatedWork W1976402971 @default.
- W2891632051 hasRelatedWork W2250385622 @default.
- W2891632051 hasRelatedWork W2308720496 @default.
- W2891632051 hasRelatedWork W2752868598 @default.
- W2891632051 hasRelatedWork W2791751435 @default.
- W2891632051 hasRelatedWork W2891632051 @default.
- W2891632051 hasRelatedWork W2951625590 @default.
- W2891632051 hasRelatedWork W2952644835 @default.
- W2891632051 hasRelatedWork W4300721532 @default.
- W2891632051 hasRelatedWork W187155384 @default.
- W2891632051 hasVolume "33" @default.
- W2891632051 isParatext "false" @default.
- W2891632051 isRetracted "false" @default.
- W2891632051 magId "2891632051" @default.
- W2891632051 workType "article" @default.