FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089872600> ?p ?o ?g. }

• W3089872600 endingPage "277" @default.
• W3089872600 startingPage "249" @default.
• W3089872600 abstract "With the rapid development of knowledge bases (KBs), question answering (QA) based on KBs has become a hot research issue. The KB-QA technology can be divided into two technical routes: (1) symbol based representations, such as traditional semantic parsing, and (2) distribution based embedding. With the emergence of deep learning, the development of NLP has greatly promoted. The effect of KB-QA can be improved by combining deep learning with the above two technical routes respectively. In this paper, the impact of the second route (i.e., Distribution Embedding) combined with deep learning is mainly discussed. This route can be divided into pipeline frameworks and end-to-end frameworks. For comprehensive analysis, two frameworks (i.e., a pipeline framework, an end-to-end framework) are proposed to focus on answering single-relation factoid questions. In both of two frameworks, the effect of context information on the quality of QA is studied, such as the entity’s notable type, out-degree. In the pipeline framework, it includes two cascaded steps: entity detection and relation detection. In this framework, multiple modules need to be built, and corresponding training data sets must be constructed for them respectively. The entire process of the pipleine framework is complex, costly and has the problem of error propagation. In the end-to-end framework, the two subtasks of entity detection and relation detection are merged together, and then combined into one framework. Questions, entities and relations are mapped into the same semantic space through the encoding of the recurrent neural network. Moreover, the question-entity similarity and the question-relation similarity are calculated, so that the candidate answers can be sorted and selected. Moreover, character-level(char-level) encoding and self-attention mechanisms are combined using weight sharing and multi-task strategies to enhance the accuracy of QA. Experimental results show that context information can get better results of simple QA whether it is the pipeline framework or the end-to-end framework. In addition, the end-to-end framework achieves results competitive with state-of-the-art approaches in terms of accuracy." @default.
• W3089872600 created "2020-10-08" @default.
• W3089872600 creator A5010830153 @default.
• W3089872600 creator A5016677170 @default.
• W3089872600 creator A5058965019 @default.
• W3089872600 creator A5076088590 @default.
• W3089872600 date "2020-10-01" @default.
• W3089872600 modified "2023-10-01" @default.
• W3089872600 title "Using context information to enhance simple question answering" @default.
• W3089872600 cites W102708294 @default.
• W3089872600 cites W1514778210 @default.
• W3089872600 cites W1662296157 @default.
• W3089872600 cites W1801721664 @default.
• W3089872600 cites W1802829841 @default.
• W3089872600 cites W1902237438 @default.
• W3089872600 cites W2015191210 @default.
• W3089872600 cites W2016753842 @default.
• W3089872600 cites W2022166150 @default.
• W3089872600 cites W2064675550 @default.
• W3089872600 cites W2079735306 @default.
• W3089872600 cites W2080133951 @default.
• W3089872600 cites W2094728533 @default.
• W3089872600 cites W2120699290 @default.
• W3089872600 cites W2161002933 @default.
• W3089872600 cites W2250539671 @default.
• W3089872600 cites W2250630028 @default.
• W3089872600 cites W2251143283 @default.
• W3089872600 cites W2267186426 @default.
• W3089872600 cites W2516255829 @default.
• W3089872600 cites W2556468274 @default.
• W3089872600 cites W2559114258 @default.
• W3089872600 cites W2605089588 @default.
• W3089872600 cites W2620787630 @default.
• W3089872600 cites W2625961748 @default.
• W3089872600 cites W2738486593 @default.
• W3089872600 cites W2739716023 @default.
• W3089872600 cites W2759281352 @default.
• W3089872600 cites W2776125440 @default.
• W3089872600 cites W2791779647 @default.
• W3089872600 cites W2887057599 @default.
• W3089872600 cites W2890494507 @default.
• W3089872600 cites W2890498499 @default.
• W3089872600 cites W2891467353 @default.
• W3089872600 cites W2902551236 @default.
• W3089872600 cites W2906502833 @default.
• W3089872600 cites W2963706742 @default.
• W3089872600 cites W2963738886 @default.
• W3089872600 cites W2964199361 @default.
• W3089872600 cites W3099235767 @default.
• W3089872600 cites W3105204788 @default.
• W3089872600 cites W2798566863 @default.
• W3089872600 doi "https://doi.org/10.1007/s11280-020-00842-7" @default.
• W3089872600 hasPublicationYear "2020" @default.
• W3089872600 type Work @default.
• W3089872600 sameAs 3089872600 @default.
• W3089872600 citedByCount "8" @default.
• W3089872600 countsByYear W30898726002021 @default.
• W3089872600 countsByYear W30898726002022 @default.
• W3089872600 countsByYear W30898726002023 @default.
• W3089872600 crossrefType "journal-article" @default.
• W3089872600 hasAuthorship W3089872600A5010830153 @default.
• W3089872600 hasAuthorship W3089872600A5016677170 @default.
• W3089872600 hasAuthorship W3089872600A5058965019 @default.
• W3089872600 hasAuthorship W3089872600A5076088590 @default.
• W3089872600 hasBestOaLocation W30898726002 @default.
• W3089872600 hasConcept C108583219 @default.
• W3089872600 hasConcept C111919701 @default.
• W3089872600 hasConcept C120665830 @default.
• W3089872600 hasConcept C121332964 @default.
• W3089872600 hasConcept C124101348 @default.
• W3089872600 hasConcept C151730666 @default.
• W3089872600 hasConcept C154945302 @default.
• W3089872600 hasConcept C186644900 @default.
• W3089872600 hasConcept C192209626 @default.
• W3089872600 hasConcept C199360897 @default.
• W3089872600 hasConcept C204321447 @default.
• W3089872600 hasConcept C23123220 @default.
• W3089872600 hasConcept C25343380 @default.
• W3089872600 hasConcept C2779343474 @default.
• W3089872600 hasConcept C41008148 @default.
• W3089872600 hasConcept C41608201 @default.
• W3089872600 hasConcept C43521106 @default.
• W3089872600 hasConcept C44291984 @default.
• W3089872600 hasConcept C86803240 @default.
• W3089872600 hasConcept C98045186 @default.
• W3089872600 hasConceptScore W3089872600C108583219 @default.
• W3089872600 hasConceptScore W3089872600C111919701 @default.
• W3089872600 hasConceptScore W3089872600C120665830 @default.
• W3089872600 hasConceptScore W3089872600C121332964 @default.
• W3089872600 hasConceptScore W3089872600C124101348 @default.
• W3089872600 hasConceptScore W3089872600C151730666 @default.
• W3089872600 hasConceptScore W3089872600C154945302 @default.
• W3089872600 hasConceptScore W3089872600C186644900 @default.
• W3089872600 hasConceptScore W3089872600C192209626 @default.
• W3089872600 hasConceptScore W3089872600C199360897 @default.
• W3089872600 hasConceptScore W3089872600C204321447 @default.
• W3089872600 hasConceptScore W3089872600C23123220 @default.
• W3089872600 hasConceptScore W3089872600C25343380 @default.

• next