Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885103667> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2885103667 abstract "State-of-the-art systems in deep question answering proceed as follows: (1) an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer. Yet the exact interplay between both components is poorly understood, especially concerning the number of candidate documents that should be retrieved. We show that choosing a static number of documents -- as used in prior research -- suffers from a noise-information trade-off and yields suboptimal results. As a remedy, we propose an adaptive document retrieval model. This learns the optimal candidate number for document retrieval, conditional on the size of the corpus and the query. We report extensive experimental results showing that our adaptive approach outperforms state-of-the-art methods on multiple benchmark datasets, as well as in the context of corpora with variable sizes." @default.
- W2885103667 created "2018-08-22" @default.
- W2885103667 creator A5034621580 @default.
- W2885103667 creator A5081442873 @default.
- W2885103667 date "2018-08-20" @default.
- W2885103667 modified "2023-09-27" @default.
- W2885103667 title "Adaptive Document Retrieval for Deep Question Answering." @default.
- W2885103667 cites W1717702867 @default.
- W2885103667 cites W1801866228 @default.
- W2885103667 cites W1986641982 @default.
- W2885103667 cites W2029118765 @default.
- W2885103667 cites W207835658 @default.
- W2885103667 cites W2087227067 @default.
- W2885103667 cites W2104582871 @default.
- W2885103667 cites W2115758952 @default.
- W2885103667 cites W2151149636 @default.
- W2885103667 cites W2252136820 @default.
- W2885103667 cites W2409591106 @default.
- W2885103667 cites W2427527485 @default.
- W2885103667 cites W2765390718 @default.
- W2885103667 cites W2788448041 @default.
- W2885103667 cites W2798211964 @default.
- W2885103667 hasPublicationYear "2018" @default.
- W2885103667 type Work @default.
- W2885103667 sameAs 2885103667 @default.
- W2885103667 citedByCount "4" @default.
- W2885103667 countsByYear W28851036672018 @default.
- W2885103667 countsByYear W28851036672019 @default.
- W2885103667 countsByYear W28851036672020 @default.
- W2885103667 countsByYear W28851036672021 @default.
- W2885103667 crossrefType "posted-content" @default.
- W2885103667 hasAuthorship W2885103667A5034621580 @default.
- W2885103667 hasAuthorship W2885103667A5081442873 @default.
- W2885103667 hasConcept C13280743 @default.
- W2885103667 hasConcept C151730666 @default.
- W2885103667 hasConcept C154945302 @default.
- W2885103667 hasConcept C161156560 @default.
- W2885103667 hasConcept C185798385 @default.
- W2885103667 hasConcept C205649164 @default.
- W2885103667 hasConcept C23123220 @default.
- W2885103667 hasConcept C2779343474 @default.
- W2885103667 hasConcept C2984842247 @default.
- W2885103667 hasConcept C41008148 @default.
- W2885103667 hasConcept C44291984 @default.
- W2885103667 hasConcept C50644808 @default.
- W2885103667 hasConcept C86803240 @default.
- W2885103667 hasConceptScore W2885103667C13280743 @default.
- W2885103667 hasConceptScore W2885103667C151730666 @default.
- W2885103667 hasConceptScore W2885103667C154945302 @default.
- W2885103667 hasConceptScore W2885103667C161156560 @default.
- W2885103667 hasConceptScore W2885103667C185798385 @default.
- W2885103667 hasConceptScore W2885103667C205649164 @default.
- W2885103667 hasConceptScore W2885103667C23123220 @default.
- W2885103667 hasConceptScore W2885103667C2779343474 @default.
- W2885103667 hasConceptScore W2885103667C2984842247 @default.
- W2885103667 hasConceptScore W2885103667C41008148 @default.
- W2885103667 hasConceptScore W2885103667C44291984 @default.
- W2885103667 hasConceptScore W2885103667C50644808 @default.
- W2885103667 hasConceptScore W2885103667C86803240 @default.
- W2885103667 hasLocation W28851036671 @default.
- W2885103667 hasOpenAccess W2885103667 @default.
- W2885103667 hasPrimaryLocation W28851036671 @default.
- W2885103667 hasRelatedWork W1539972817 @default.
- W2885103667 hasRelatedWork W1554694706 @default.
- W2885103667 hasRelatedWork W18398563 @default.
- W2885103667 hasRelatedWork W1964241209 @default.
- W2885103667 hasRelatedWork W1992739863 @default.
- W2885103667 hasRelatedWork W2000610566 @default.
- W2885103667 hasRelatedWork W2037098674 @default.
- W2885103667 hasRelatedWork W2081907690 @default.
- W2885103667 hasRelatedWork W2102046030 @default.
- W2885103667 hasRelatedWork W2283472011 @default.
- W2885103667 hasRelatedWork W25192062 @default.
- W2885103667 hasRelatedWork W2768459074 @default.
- W2885103667 hasRelatedWork W2796282752 @default.
- W2885103667 hasRelatedWork W2809517355 @default.
- W2885103667 hasRelatedWork W2912364477 @default.
- W2885103667 hasRelatedWork W2937036051 @default.
- W2885103667 hasRelatedWork W2962865973 @default.
- W2885103667 hasRelatedWork W3094064346 @default.
- W2885103667 hasRelatedWork W3166576616 @default.
- W2885103667 hasRelatedWork W3175045046 @default.
- W2885103667 isParatext "false" @default.
- W2885103667 isRetracted "false" @default.
- W2885103667 magId "2885103667" @default.
- W2885103667 workType "article" @default.