FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119975768> ?p ?o ?g. }

• W3119975768 endingPage "8171" @default.
• W3119975768 startingPage "8163" @default.
• W3119975768 abstract "Logical reasoning tasks over symbols, such as learning arithmetic operations and computer program evaluations, have become challenges to deep learning. In particular, even state-of-the-art neural networks fail to achieve textit{out-of-distribution} (OOD) generalization of symbolic reasoning tasks, whereas humans can easily extend learned symbolic rules. To resolve this difficulty, we propose a neural sequence-to-grid (seq2grid) module, an input preprocessor that automatically segments and aligns an input sequence into a grid. As our module outputs a grid via a novel differentiable mapping, any neural network structure taking a grid input, such as ResNet or TextCNN, can be jointly trained with our module in an end-to-end fashion. Extensive experiments show that neural networks having our module as an input preprocessor achieve OOD generalization on various arithmetic and algorithmic problems including number sequence prediction problems, algebraic word problems, and computer program evaluation problems while other state-of-the-art sequence transduction models cannot. Moreover, we verify that our module enhances TextCNN to solve the bAbI QA tasks without external memory." @default.
• W3119975768 created "2021-01-18" @default.
• W3119975768 creator A5025937126 @default.
• W3119975768 creator A5026151562 @default.
• W3119975768 creator A5068440432 @default.
• W3119975768 creator A5077832834 @default.
• W3119975768 date "2021-05-18" @default.
• W3119975768 modified "2023-10-16" @default.
• W3119975768 title "Neural Sequence-to-grid Module for Learning Symbolic Rules" @default.
• W3119975768 cites W1522301498 @default.
• W3119975768 cites W1525961042 @default.
• W3119975768 cites W1581407678 @default.
• W3119975768 cites W1602017060 @default.
• W3119975768 cites W1699946128 @default.
• W3119975768 cites W1732222442 @default.
• W3119975768 cites W1771459135 @default.
• W3119975768 cites W2130942839 @default.
• W3119975768 cites W2133564696 @default.
• W3119975768 cites W2173051530 @default.
• W3119975768 cites W2194690080 @default.
• W3119975768 cites W2194775991 @default.
• W3119975768 cites W2530887700 @default.
• W3119975768 cites W2540419089 @default.
• W3119975768 cites W2607964821 @default.
• W3119975768 cites W2757276219 @default.
• W3119975768 cites W2787457957 @default.
• W3119975768 cites W2887020936 @default.
• W3119975768 cites W2899861731 @default.
• W3119975768 cites W2905270607 @default.
• W3119975768 cites W2912007050 @default.
• W3119975768 cites W2949541494 @default.
• W3119975768 cites W2949718784 @default.
• W3119975768 cites W2950527759 @default.
• W3119975768 cites W2951107864 @default.
• W3119975768 cites W2963267799 @default.
• W3119975768 cites W2963403868 @default.
• W3119975768 cites W2963870701 @default.
• W3119975768 cites W2970555085 @default.
• W3119975768 cites W2994278562 @default.
• W3119975768 cites W2995628494 @default.
• W3119975768 cites W2996132992 @default.
• W3119975768 cites W3037664376 @default.
• W3119975768 doi "https://doi.org/10.1609/aaai.v35i9.16994" @default.
• W3119975768 hasPublicationYear "2021" @default.
• W3119975768 type Work @default.
• W3119975768 sameAs 3119975768 @default.
• W3119975768 citedByCount "3" @default.
• W3119975768 countsByYear W31199757682021 @default.
• W3119975768 countsByYear W31199757682022 @default.
• W3119975768 crossrefType "journal-article" @default.
• W3119975768 hasAuthorship W3119975768A5025937126 @default.
• W3119975768 hasAuthorship W3119975768A5026151562 @default.
• W3119975768 hasAuthorship W3119975768A5068440432 @default.
• W3119975768 hasAuthorship W3119975768A5077832834 @default.
• W3119975768 hasBestOaLocation W31199757681 @default.
• W3119975768 hasConcept C134306372 @default.
• W3119975768 hasConcept C154945302 @default.
• W3119975768 hasConcept C177148314 @default.
• W3119975768 hasConcept C187691185 @default.
• W3119975768 hasConcept C2524010 @default.
• W3119975768 hasConcept C2778112365 @default.
• W3119975768 hasConcept C33923547 @default.
• W3119975768 hasConcept C34736171 @default.
• W3119975768 hasConcept C40506919 @default.
• W3119975768 hasConcept C41008148 @default.
• W3119975768 hasConcept C50644808 @default.
• W3119975768 hasConcept C54355233 @default.
• W3119975768 hasConcept C80444323 @default.
• W3119975768 hasConcept C86803240 @default.
• W3119975768 hasConcept C90805587 @default.
• W3119975768 hasConceptScore W3119975768C134306372 @default.
• W3119975768 hasConceptScore W3119975768C154945302 @default.
• W3119975768 hasConceptScore W3119975768C177148314 @default.
• W3119975768 hasConceptScore W3119975768C187691185 @default.
• W3119975768 hasConceptScore W3119975768C2524010 @default.
• W3119975768 hasConceptScore W3119975768C2778112365 @default.
• W3119975768 hasConceptScore W3119975768C33923547 @default.
• W3119975768 hasConceptScore W3119975768C34736171 @default.
• W3119975768 hasConceptScore W3119975768C40506919 @default.
• W3119975768 hasConceptScore W3119975768C41008148 @default.
• W3119975768 hasConceptScore W3119975768C50644808 @default.
• W3119975768 hasConceptScore W3119975768C54355233 @default.
• W3119975768 hasConceptScore W3119975768C80444323 @default.
• W3119975768 hasConceptScore W3119975768C86803240 @default.
• W3119975768 hasConceptScore W3119975768C90805587 @default.
• W3119975768 hasIssue "9" @default.
• W3119975768 hasLocation W31199757681 @default.
• W3119975768 hasLocation W31199757682 @default.
• W3119975768 hasOpenAccess W3119975768 @default.
• W3119975768 hasPrimaryLocation W31199757681 @default.
• W3119975768 hasRelatedWork W2037890446 @default.
• W3119975768 hasRelatedWork W2360025963 @default.
• W3119975768 hasRelatedWork W2382928216 @default.
• W3119975768 hasRelatedWork W2790589292 @default.
• W3119975768 hasRelatedWork W2950129230 @default.
• W3119975768 hasRelatedWork W2964123521 @default.
• W3119975768 hasRelatedWork W2990379018 @default.
• W3119975768 hasRelatedWork W3011524177 @default.

• next