Matches in SemOpenAlex for { <https://semopenalex.org/work/W2802103240> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2802103240 abstract "We present an end-to-end multi-scale Convolutional Neural Network (CNN) framework for topic identification (topic ID). In this work, we examined multi -scale CNN for classification using raw text input. Topical word embeddings are learnt at multiple scales using parallel convolutional layers. A technique to integrate verification and identification objectives is examined to improve topic ID performance. With this approach, we achieved significant improvement in identification task. We evaluated our framework on two contrasting datasets: 20 newsgroups and Fisher. We obtained 92.93% accuracy on Fisher and 86.12% on 20 newsgroups, which to our know ledge are the best published results on these datasets at the moment." @default.
- W2802103240 created "2018-05-17" @default.
- W2802103240 creator A5040448607 @default.
- W2802103240 creator A5050632169 @default.
- W2802103240 creator A5057010207 @default.
- W2802103240 date "2018-04-01" @default.
- W2802103240 modified "2023-10-13" @default.
- W2802103240 title "Joint Verification-Identification in end-to-end Multi-Scale CNN Framework for Topic Identification" @default.
- W2802103240 cites W1964155876 @default.
- W2802103240 cites W1998808035 @default.
- W2802103240 cites W2120615054 @default.
- W2802103240 cites W2168363555 @default.
- W2802103240 cites W2518058337 @default.
- W2802103240 cites W2558960030 @default.
- W2802103240 cites W2587150483 @default.
- W2802103240 cites W2616922365 @default.
- W2802103240 doi "https://doi.org/10.1109/icassp.2018.8461673" @default.
- W2802103240 hasPublicationYear "2018" @default.
- W2802103240 type Work @default.
- W2802103240 sameAs 2802103240 @default.
- W2802103240 citedByCount "12" @default.
- W2802103240 countsByYear W28021032402019 @default.
- W2802103240 countsByYear W28021032402020 @default.
- W2802103240 countsByYear W28021032402021 @default.
- W2802103240 countsByYear W28021032402022 @default.
- W2802103240 countsByYear W28021032402023 @default.
- W2802103240 crossrefType "proceedings-article" @default.
- W2802103240 hasAuthorship W2802103240A5040448607 @default.
- W2802103240 hasAuthorship W2802103240A5050632169 @default.
- W2802103240 hasAuthorship W2802103240A5057010207 @default.
- W2802103240 hasConcept C116834253 @default.
- W2802103240 hasConcept C119857082 @default.
- W2802103240 hasConcept C121332964 @default.
- W2802103240 hasConcept C124101348 @default.
- W2802103240 hasConcept C127413603 @default.
- W2802103240 hasConcept C153180895 @default.
- W2802103240 hasConcept C154945302 @default.
- W2802103240 hasConcept C201995342 @default.
- W2802103240 hasConcept C2778755073 @default.
- W2802103240 hasConcept C2780451532 @default.
- W2802103240 hasConcept C41008148 @default.
- W2802103240 hasConcept C59822182 @default.
- W2802103240 hasConcept C62520636 @default.
- W2802103240 hasConcept C74296488 @default.
- W2802103240 hasConcept C81363708 @default.
- W2802103240 hasConcept C86803240 @default.
- W2802103240 hasConceptScore W2802103240C116834253 @default.
- W2802103240 hasConceptScore W2802103240C119857082 @default.
- W2802103240 hasConceptScore W2802103240C121332964 @default.
- W2802103240 hasConceptScore W2802103240C124101348 @default.
- W2802103240 hasConceptScore W2802103240C127413603 @default.
- W2802103240 hasConceptScore W2802103240C153180895 @default.
- W2802103240 hasConceptScore W2802103240C154945302 @default.
- W2802103240 hasConceptScore W2802103240C201995342 @default.
- W2802103240 hasConceptScore W2802103240C2778755073 @default.
- W2802103240 hasConceptScore W2802103240C2780451532 @default.
- W2802103240 hasConceptScore W2802103240C41008148 @default.
- W2802103240 hasConceptScore W2802103240C59822182 @default.
- W2802103240 hasConceptScore W2802103240C62520636 @default.
- W2802103240 hasConceptScore W2802103240C74296488 @default.
- W2802103240 hasConceptScore W2802103240C81363708 @default.
- W2802103240 hasConceptScore W2802103240C86803240 @default.
- W2802103240 hasLocation W28021032401 @default.
- W2802103240 hasOpenAccess W2802103240 @default.
- W2802103240 hasPrimaryLocation W28021032401 @default.
- W2802103240 hasRelatedWork W1999612375 @default.
- W2802103240 hasRelatedWork W2151749779 @default.
- W2802103240 hasRelatedWork W2938107654 @default.
- W2802103240 hasRelatedWork W3008587939 @default.
- W2802103240 hasRelatedWork W3127005940 @default.
- W2802103240 hasRelatedWork W3179968364 @default.
- W2802103240 hasRelatedWork W3196421258 @default.
- W2802103240 hasRelatedWork W4293226380 @default.
- W2802103240 hasRelatedWork W4313906399 @default.
- W2802103240 hasRelatedWork W4387301579 @default.
- W2802103240 isParatext "false" @default.
- W2802103240 isRetracted "false" @default.
- W2802103240 magId "2802103240" @default.
- W2802103240 workType "article" @default.