Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898858752> ?p ?o ?g. }
- W2898858752 abstract "Machine reading comprehension helps machines learn to utilize most of the human knowledge written in the form of text. Existing approaches made a significant progress comparable to human-level performance, but they are still limited in understanding, up to a few paragraphs, failing to properly comprehend lengthy document. In this paper, we propose a novel deep neural network architecture to handle a long-range dependency in RC tasks. In detail, our method has two novel aspects: (1) an advanced memory-augmented architecture and (2) an expanded gated recurrent unit with dense connections that mitigate potential information distortion occurring in the memory. Our proposed architecture is widely applicable to other models. We have performed extensive experiments with well-known benchmark datasets such as TriviaQA, QUASAR-T, and SQuAD. The experimental results demonstrate that the proposed method outperforms existing methods, especially for lengthy documents." @default.
- W2898858752 created "2018-11-09" @default.
- W2898858752 creator A5014603190 @default.
- W2898858752 creator A5036671957 @default.
- W2898858752 creator A5047912015 @default.
- W2898858752 creator A5052409554 @default.
- W2898858752 creator A5080664764 @default.
- W2898858752 date "2018-01-01" @default.
- W2898858752 modified "2023-09-25" @default.
- W2898858752 title "MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller" @default.
- W2898858752 cites W1525961042 @default.
- W2898858752 cites W2143017621 @default.
- W2898858752 cites W2157331557 @default.
- W2898858752 cites W2250539671 @default.
- W2898858752 cites W2551396370 @default.
- W2898858752 cites W2563734883 @default.
- W2898858752 cites W2626154462 @default.
- W2898858752 cites W2734823783 @default.
- W2898858752 cites W2739749670 @default.
- W2898858752 cites W2740747242 @default.
- W2898858752 cites W2752104716 @default.
- W2898858752 cites W2765627424 @default.
- W2898858752 cites W2766508367 @default.
- W2898858752 cites W2798858969 @default.
- W2898858752 cites W2887557046 @default.
- W2898858752 cites W2950527759 @default.
- W2898858752 cites W2962718483 @default.
- W2898858752 cites W2962739339 @default.
- W2898858752 cites W2962809918 @default.
- W2898858752 cites W2962985038 @default.
- W2898858752 cites W2963082277 @default.
- W2898858752 cites W2963339397 @default.
- W2898858752 cites W2963446712 @default.
- W2898858752 cites W2963748441 @default.
- W2898858752 cites W2963769536 @default.
- W2898858752 cites W2963871484 @default.
- W2898858752 cites W6908809 @default.
- W2898858752 doi "https://doi.org/10.18653/v1/d18-1237" @default.
- W2898858752 hasPublicationYear "2018" @default.
- W2898858752 type Work @default.
- W2898858752 sameAs 2898858752 @default.
- W2898858752 citedByCount "12" @default.
- W2898858752 countsByYear W28988587522019 @default.
- W2898858752 countsByYear W28988587522020 @default.
- W2898858752 countsByYear W28988587522021 @default.
- W2898858752 countsByYear W28988587522022 @default.
- W2898858752 crossrefType "proceedings-article" @default.
- W2898858752 hasAuthorship W2898858752A5014603190 @default.
- W2898858752 hasAuthorship W2898858752A5036671957 @default.
- W2898858752 hasAuthorship W2898858752A5047912015 @default.
- W2898858752 hasAuthorship W2898858752A5052409554 @default.
- W2898858752 hasAuthorship W2898858752A5080664764 @default.
- W2898858752 hasBestOaLocation W28988587521 @default.
- W2898858752 hasConcept C119857082 @default.
- W2898858752 hasConcept C123657996 @default.
- W2898858752 hasConcept C13280743 @default.
- W2898858752 hasConcept C142362112 @default.
- W2898858752 hasConcept C153349607 @default.
- W2898858752 hasConcept C154945302 @default.
- W2898858752 hasConcept C17744445 @default.
- W2898858752 hasConcept C185798385 @default.
- W2898858752 hasConcept C19768560 @default.
- W2898858752 hasConcept C199360897 @default.
- W2898858752 hasConcept C199539241 @default.
- W2898858752 hasConcept C204321447 @default.
- W2898858752 hasConcept C205649164 @default.
- W2898858752 hasConcept C2778780117 @default.
- W2898858752 hasConcept C41008148 @default.
- W2898858752 hasConcept C511192102 @default.
- W2898858752 hasConcept C554936623 @default.
- W2898858752 hasConceptScore W2898858752C119857082 @default.
- W2898858752 hasConceptScore W2898858752C123657996 @default.
- W2898858752 hasConceptScore W2898858752C13280743 @default.
- W2898858752 hasConceptScore W2898858752C142362112 @default.
- W2898858752 hasConceptScore W2898858752C153349607 @default.
- W2898858752 hasConceptScore W2898858752C154945302 @default.
- W2898858752 hasConceptScore W2898858752C17744445 @default.
- W2898858752 hasConceptScore W2898858752C185798385 @default.
- W2898858752 hasConceptScore W2898858752C19768560 @default.
- W2898858752 hasConceptScore W2898858752C199360897 @default.
- W2898858752 hasConceptScore W2898858752C199539241 @default.
- W2898858752 hasConceptScore W2898858752C204321447 @default.
- W2898858752 hasConceptScore W2898858752C205649164 @default.
- W2898858752 hasConceptScore W2898858752C2778780117 @default.
- W2898858752 hasConceptScore W2898858752C41008148 @default.
- W2898858752 hasConceptScore W2898858752C511192102 @default.
- W2898858752 hasConceptScore W2898858752C554936623 @default.
- W2898858752 hasLocation W28988587521 @default.
- W2898858752 hasOpenAccess W2898858752 @default.
- W2898858752 hasPrimaryLocation W28988587521 @default.
- W2898858752 hasRelatedWork W1483367581 @default.
- W2898858752 hasRelatedWork W1969359128 @default.
- W2898858752 hasRelatedWork W1982811735 @default.
- W2898858752 hasRelatedWork W2122416217 @default.
- W2898858752 hasRelatedWork W2389366623 @default.
- W2898858752 hasRelatedWork W2511797247 @default.
- W2898858752 hasRelatedWork W2524839221 @default.
- W2898858752 hasRelatedWork W272600498 @default.
- W2898858752 hasRelatedWork W4223892844 @default.
- W2898858752 hasRelatedWork W44286443 @default.