Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091348480> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3091348480 abstract "Multi-paragraph reading comprehension requires the model to infer answers of arbitrary user-generated questions by reasoning cross-passage information. Previous work usually generates answer by directly employing a pointer network to predict the start and end position of the answer. However, span-level reading is insufficient since intermediate words may matter more. In this paper, we propose a novel unified network that includes a selector, a Token-level dynamic reader, and a Hybrid verifier (TH-Net). The core of token-level dynamic reader is a gate mechanism which dynamically selects important intermediate words according to boundary words. We decide the reader score from each token being both the boundary and the content. Moreover, we adopt a hybrid network verifier considering semantic answer-answer and entailment question-answer relationships to robust the model in case of being fooled by adversarial answers. Our experiments on SQuAD-document, SQuAD-open, and Trivia-wiki datasets show significant and consistent improvement as compared to other baselines and achieve the state-of-the-art performance on two of them." @default.
- W3091348480 created "2020-10-08" @default.
- W3091348480 creator A5054901507 @default.
- W3091348480 creator A5068916634 @default.
- W3091348480 creator A5085695760 @default.
- W3091348480 creator A5091659586 @default.
- W3091348480 date "2020-07-01" @default.
- W3091348480 modified "2023-10-16" @default.
- W3091348480 title "Multi-paragraph Reading Comprehension with Token-level Dynamic Reader and Hybrid Verifier" @default.
- W3091348480 cites W1832693441 @default.
- W3091348480 cites W2510759893 @default.
- W3091348480 cites W2759477115 @default.
- W3091348480 cites W2799081691 @default.
- W3091348480 cites W2949847757 @default.
- W3091348480 cites W2951561177 @default.
- W3091348480 cites W2962718483 @default.
- W3091348480 cites W2962808855 @default.
- W3091348480 cites W2962985038 @default.
- W3091348480 cites W2963159735 @default.
- W3091348480 cites W2963246595 @default.
- W3091348480 cites W2963323070 @default.
- W3091348480 cites W2963339397 @default.
- W3091348480 cites W2963547127 @default.
- W3091348480 cites W2963748441 @default.
- W3091348480 cites W2963898730 @default.
- W3091348480 cites W2963969878 @default.
- W3091348480 cites W2964181805 @default.
- W3091348480 cites W2964222246 @default.
- W3091348480 cites W2964348592 @default.
- W3091348480 cites W3103111734 @default.
- W3091348480 doi "https://doi.org/10.1109/ijcnn48605.2020.9206859" @default.
- W3091348480 hasPublicationYear "2020" @default.
- W3091348480 type Work @default.
- W3091348480 sameAs 3091348480 @default.
- W3091348480 citedByCount "1" @default.
- W3091348480 countsByYear W30913484802022 @default.
- W3091348480 crossrefType "proceedings-article" @default.
- W3091348480 hasAuthorship W3091348480A5054901507 @default.
- W3091348480 hasAuthorship W3091348480A5068916634 @default.
- W3091348480 hasAuthorship W3091348480A5085695760 @default.
- W3091348480 hasAuthorship W3091348480A5091659586 @default.
- W3091348480 hasConcept C136764020 @default.
- W3091348480 hasConcept C138885662 @default.
- W3091348480 hasConcept C2777206241 @default.
- W3091348480 hasConcept C2778780117 @default.
- W3091348480 hasConcept C38652104 @default.
- W3091348480 hasConcept C41008148 @default.
- W3091348480 hasConcept C41895202 @default.
- W3091348480 hasConcept C48145219 @default.
- W3091348480 hasConcept C554936623 @default.
- W3091348480 hasConceptScore W3091348480C136764020 @default.
- W3091348480 hasConceptScore W3091348480C138885662 @default.
- W3091348480 hasConceptScore W3091348480C2777206241 @default.
- W3091348480 hasConceptScore W3091348480C2778780117 @default.
- W3091348480 hasConceptScore W3091348480C38652104 @default.
- W3091348480 hasConceptScore W3091348480C41008148 @default.
- W3091348480 hasConceptScore W3091348480C41895202 @default.
- W3091348480 hasConceptScore W3091348480C48145219 @default.
- W3091348480 hasConceptScore W3091348480C554936623 @default.
- W3091348480 hasLocation W30913484801 @default.
- W3091348480 hasOpenAccess W3091348480 @default.
- W3091348480 hasPrimaryLocation W30913484801 @default.
- W3091348480 hasRelatedWork W2004783491 @default.
- W3091348480 hasRelatedWork W2073813715 @default.
- W3091348480 hasRelatedWork W2134971061 @default.
- W3091348480 hasRelatedWork W2375389409 @default.
- W3091348480 hasRelatedWork W2384709979 @default.
- W3091348480 hasRelatedWork W2387134327 @default.
- W3091348480 hasRelatedWork W2597694933 @default.
- W3091348480 hasRelatedWork W3009520549 @default.
- W3091348480 hasRelatedWork W3202519082 @default.
- W3091348480 hasRelatedWork W868239154 @default.
- W3091348480 isParatext "false" @default.
- W3091348480 isRetracted "false" @default.
- W3091348480 magId "3091348480" @default.
- W3091348480 workType "article" @default.