Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014887788> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3014887788 endingPage "141" @default.
- W3014887788 startingPage "132" @default.
- W3014887788 abstract "Convolutional neural networks are one of the most important and widely used constructs in natural language processing and AI in general. In many applications, they have achieved state-of-the-art performance, with training time faster than the other alternatives. However, due to their limited interpretability, they are less favored by practitioners over attention-based models, like RNNs and self-attention (Transformers), which can be visualized and interpreted more intuitively by analyzing the attention-weight heat-maps. In this work, we present a visualization technique that can be used to understand the inner workings of text-based CNN models. We also show how this method can be used to generate adversarial examples and learn the shortcomings of the training data." @default.
- W3014887788 created "2020-04-10" @default.
- W3014887788 creator A5024475514 @default.
- W3014887788 creator A5065630217 @default.
- W3014887788 creator A5076622540 @default.
- W3014887788 date "2020-06-01" @default.
- W3014887788 modified "2023-10-12" @default.
- W3014887788 title "Token-wise sentiment decomposition for ConvNet: Visualizing a sentiment classifier" @default.
- W3014887788 cites W1569397376 @default.
- W3014887788 cites W1787224781 @default.
- W3014887788 cites W2118960450 @default.
- W3014887788 cites W2343061342 @default.
- W3014887788 cites W2512304460 @default.
- W3014887788 cites W2561412020 @default.
- W3014887788 cites W2751627669 @default.
- W3014887788 cites W2752194699 @default.
- W3014887788 cites W2772121968 @default.
- W3014887788 cites W2936427306 @default.
- W3014887788 cites W2950856799 @default.
- W3014887788 cites W2962883557 @default.
- W3014887788 cites W2963123635 @default.
- W3014887788 cites W2964303497 @default.
- W3014887788 cites W4247200422 @default.
- W3014887788 doi "https://doi.org/10.1016/j.visinf.2020.04.006" @default.
- W3014887788 hasPublicationYear "2020" @default.
- W3014887788 type Work @default.
- W3014887788 sameAs 3014887788 @default.
- W3014887788 citedByCount "4" @default.
- W3014887788 countsByYear W30148877882020 @default.
- W3014887788 countsByYear W30148877882021 @default.
- W3014887788 countsByYear W30148877882023 @default.
- W3014887788 crossrefType "journal-article" @default.
- W3014887788 hasAuthorship W3014887788A5024475514 @default.
- W3014887788 hasAuthorship W3014887788A5065630217 @default.
- W3014887788 hasAuthorship W3014887788A5076622540 @default.
- W3014887788 hasBestOaLocation W30148877881 @default.
- W3014887788 hasConcept C108583219 @default.
- W3014887788 hasConcept C119857082 @default.
- W3014887788 hasConcept C121332964 @default.
- W3014887788 hasConcept C154945302 @default.
- W3014887788 hasConcept C165801399 @default.
- W3014887788 hasConcept C204321447 @default.
- W3014887788 hasConcept C2781067378 @default.
- W3014887788 hasConcept C36464697 @default.
- W3014887788 hasConcept C38652104 @default.
- W3014887788 hasConcept C41008148 @default.
- W3014887788 hasConcept C48145219 @default.
- W3014887788 hasConcept C62520636 @default.
- W3014887788 hasConcept C66322947 @default.
- W3014887788 hasConcept C66402592 @default.
- W3014887788 hasConcept C81363708 @default.
- W3014887788 hasConcept C95623464 @default.
- W3014887788 hasConceptScore W3014887788C108583219 @default.
- W3014887788 hasConceptScore W3014887788C119857082 @default.
- W3014887788 hasConceptScore W3014887788C121332964 @default.
- W3014887788 hasConceptScore W3014887788C154945302 @default.
- W3014887788 hasConceptScore W3014887788C165801399 @default.
- W3014887788 hasConceptScore W3014887788C204321447 @default.
- W3014887788 hasConceptScore W3014887788C2781067378 @default.
- W3014887788 hasConceptScore W3014887788C36464697 @default.
- W3014887788 hasConceptScore W3014887788C38652104 @default.
- W3014887788 hasConceptScore W3014887788C41008148 @default.
- W3014887788 hasConceptScore W3014887788C48145219 @default.
- W3014887788 hasConceptScore W3014887788C62520636 @default.
- W3014887788 hasConceptScore W3014887788C66322947 @default.
- W3014887788 hasConceptScore W3014887788C66402592 @default.
- W3014887788 hasConceptScore W3014887788C81363708 @default.
- W3014887788 hasConceptScore W3014887788C95623464 @default.
- W3014887788 hasIssue "2" @default.
- W3014887788 hasLocation W30148877881 @default.
- W3014887788 hasLocation W30148877882 @default.
- W3014887788 hasOpenAccess W3014887788 @default.
- W3014887788 hasPrimaryLocation W30148877881 @default.
- W3014887788 hasRelatedWork W2806259446 @default.
- W3014887788 hasRelatedWork W2905433371 @default.
- W3014887788 hasRelatedWork W3016124757 @default.
- W3014887788 hasRelatedWork W4287775347 @default.
- W3014887788 hasRelatedWork W4304700937 @default.
- W3014887788 hasRelatedWork W4310278675 @default.
- W3014887788 hasRelatedWork W4311431240 @default.
- W3014887788 hasRelatedWork W4312407344 @default.
- W3014887788 hasRelatedWork W4361193272 @default.
- W3014887788 hasRelatedWork W2963326959 @default.
- W3014887788 hasVolume "4" @default.
- W3014887788 isParatext "false" @default.
- W3014887788 isRetracted "false" @default.
- W3014887788 magId "3014887788" @default.
- W3014887788 workType "article" @default.