Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890203479> ?p ?o ?g. }
- W2890203479 abstract "Sequence encoders are crucial components in many neural architectures for learning to read and comprehend. This paper presents a new compositional encoder for reading comprehension (RC). Our proposed encoder is not only aimed at being fast but also expressive. Specifically, the key novelty behind our encoder is that it explicitly models across multiple granularities using a new dilated composition mechanism. In our approach, gating functions are learned by modeling relationships and reasoning over multi-granular sequence information, enabling compositional learning that is aware of both long and short term information. We conduct experiments on three RC datasets, showing that our proposed encoder demonstrates very promising results both as a standalone encoder as well as a complementary building block. Empirical results show that simple Bi-Attentive architectures augmented with our proposed encoder not only achieves state-of-the-art / highly competitive results but is also considerably faster than other published works." @default.
- W2890203479 created "2018-09-27" @default.
- W2890203479 creator A5026059624 @default.
- W2890203479 creator A5050386762 @default.
- W2890203479 creator A5057786383 @default.
- W2890203479 date "2018-01-01" @default.
- W2890203479 modified "2023-09-27" @default.
- W2890203479 title "Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension" @default.
- W2890203479 cites W1544827683 @default.
- W2890203479 cites W1966443646 @default.
- W2890203479 cites W2064675550 @default.
- W2890203479 cites W2157331557 @default.
- W2890203479 cites W2250539671 @default.
- W2890203479 cites W2516930406 @default.
- W2890203479 cites W2521709538 @default.
- W2890203479 cites W2540404261 @default.
- W2890203479 cites W2551396370 @default.
- W2890203479 cites W2553397501 @default.
- W2890203479 cites W2557764419 @default.
- W2890203479 cites W2593833795 @default.
- W2890203479 cites W2606964149 @default.
- W2890203479 cites W2609826708 @default.
- W2890203479 cites W2613681825 @default.
- W2890203479 cites W2626154462 @default.
- W2890203479 cites W2734823783 @default.
- W2890203479 cites W2740747242 @default.
- W2890203479 cites W2741263286 @default.
- W2890203479 cites W2751185861 @default.
- W2890203479 cites W2753329127 @default.
- W2890203479 cites W2768331480 @default.
- W2890203479 cites W2770564921 @default.
- W2890203479 cites W2785442519 @default.
- W2890203479 cites W2809324505 @default.
- W2890203479 cites W2951528484 @default.
- W2890203479 cites W2962739339 @default.
- W2890203479 cites W2962809918 @default.
- W2890203479 cites W2963241221 @default.
- W2890203479 cites W2963339397 @default.
- W2890203479 cites W2963344337 @default.
- W2890203479 cites W2963403868 @default.
- W2890203479 cites W2963595025 @default.
- W2890203479 cites W2963748441 @default.
- W2890203479 cites W2963756346 @default.
- W2890203479 cites W2963866616 @default.
- W2890203479 cites W2963871484 @default.
- W2890203479 cites W2963963993 @default.
- W2890203479 cites W2964121744 @default.
- W2890203479 doi "https://doi.org/10.18653/v1/d18-1238" @default.
- W2890203479 hasPublicationYear "2018" @default.
- W2890203479 type Work @default.
- W2890203479 sameAs 2890203479 @default.
- W2890203479 citedByCount "10" @default.
- W2890203479 countsByYear W28902034792019 @default.
- W2890203479 countsByYear W28902034792020 @default.
- W2890203479 countsByYear W28902034792022 @default.
- W2890203479 crossrefType "proceedings-article" @default.
- W2890203479 hasAuthorship W2890203479A5026059624 @default.
- W2890203479 hasAuthorship W2890203479A5050386762 @default.
- W2890203479 hasAuthorship W2890203479A5057786383 @default.
- W2890203479 hasBestOaLocation W28902034791 @default.
- W2890203479 hasConcept C111919701 @default.
- W2890203479 hasConcept C118505674 @default.
- W2890203479 hasConcept C125411270 @default.
- W2890203479 hasConcept C138885662 @default.
- W2890203479 hasConcept C154945302 @default.
- W2890203479 hasConcept C17744445 @default.
- W2890203479 hasConcept C199360897 @default.
- W2890203479 hasConcept C199539241 @default.
- W2890203479 hasConcept C204321447 @default.
- W2890203479 hasConcept C27206212 @default.
- W2890203479 hasConcept C2778112365 @default.
- W2890203479 hasConcept C2778738651 @default.
- W2890203479 hasConcept C41008148 @default.
- W2890203479 hasConcept C511192102 @default.
- W2890203479 hasConcept C54355233 @default.
- W2890203479 hasConcept C554936623 @default.
- W2890203479 hasConcept C80444323 @default.
- W2890203479 hasConcept C86803240 @default.
- W2890203479 hasConceptScore W2890203479C111919701 @default.
- W2890203479 hasConceptScore W2890203479C118505674 @default.
- W2890203479 hasConceptScore W2890203479C125411270 @default.
- W2890203479 hasConceptScore W2890203479C138885662 @default.
- W2890203479 hasConceptScore W2890203479C154945302 @default.
- W2890203479 hasConceptScore W2890203479C17744445 @default.
- W2890203479 hasConceptScore W2890203479C199360897 @default.
- W2890203479 hasConceptScore W2890203479C199539241 @default.
- W2890203479 hasConceptScore W2890203479C204321447 @default.
- W2890203479 hasConceptScore W2890203479C27206212 @default.
- W2890203479 hasConceptScore W2890203479C2778112365 @default.
- W2890203479 hasConceptScore W2890203479C2778738651 @default.
- W2890203479 hasConceptScore W2890203479C41008148 @default.
- W2890203479 hasConceptScore W2890203479C511192102 @default.
- W2890203479 hasConceptScore W2890203479C54355233 @default.
- W2890203479 hasConceptScore W2890203479C554936623 @default.
- W2890203479 hasConceptScore W2890203479C80444323 @default.
- W2890203479 hasConceptScore W2890203479C86803240 @default.
- W2890203479 hasLocation W28902034791 @default.
- W2890203479 hasOpenAccess W2890203479 @default.
- W2890203479 hasPrimaryLocation W28902034791 @default.
- W2890203479 hasRelatedWork W1544827683 @default.