FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953035981> ?p ?o ?g. }

• W2953035981 abstract "Recent neural language generation systems often hallucinate contents (i.e., producing irrelevant or contradicted facts), especially when trained on loosely corresponding pairs of the input structure and text. To mitigate this issue, we propose to integrate a language understanding module for data refinement with self-training iterations to effectively induce strong equivalence between the input data and the paired text. Experiments on the E2E challenge dataset show that our proposed framework can reduce more than 50% relative unaligned noise from the original data-text pairs. A vanilla sequence-to-sequence neural NLG model trained on the refined data has improved on content correctness compared with the current state-of-the-art ensemble generator." @default.
• W2953035981 created "2019-06-27" @default.
• W2953035981 creator A5033047776 @default.
• W2953035981 creator A5035927942 @default.
• W2953035981 creator A5054455207 @default.
• W2953035981 creator A5075012459 @default.
• W2953035981 creator A5090151187 @default.
• W2953035981 date "2019-01-01" @default.
• W2953035981 modified "2023-09-26" @default.
• W2953035981 title "A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation" @default.
• W2953035981 cites W1948566616 @default.
• W2953035981 cites W2101105183 @default.
• W2953035981 cites W2250539671 @default.
• W2953035981 cites W2556468274 @default.
• W2953035981 cites W2589218480 @default.
• W2953035981 cites W2606974598 @default.
• W2953035981 cites W2613898922 @default.
• W2953035981 cites W2739046565 @default.
• W2953035981 cites W2798367796 @default.
• W2953035981 cites W2806532810 @default.
• W2953035981 cites W2889587596 @default.
• W2953035981 cites W2896780650 @default.
• W2953035981 cites W2962729880 @default.
• W2953035981 cites W2962905474 @default.
• W2953035981 cites W2963014658 @default.
• W2953035981 cites W2963415248 @default.
• W2953035981 cites W2963672599 @default.
• W2953035981 cites W2963910262 @default.
• W2953035981 cites W2964165364 @default.
• W2953035981 doi "https://doi.org/10.18653/v1/p19-1256" @default.
• W2953035981 hasPublicationYear "2019" @default.
• W2953035981 type Work @default.
• W2953035981 sameAs 2953035981 @default.
• W2953035981 citedByCount "40" @default.
• W2953035981 countsByYear W29530359812019 @default.
• W2953035981 countsByYear W29530359812020 @default.
• W2953035981 countsByYear W29530359812021 @default.
• W2953035981 countsByYear W29530359812022 @default.
• W2953035981 countsByYear W29530359812023 @default.
• W2953035981 crossrefType "proceedings-article" @default.
• W2953035981 hasAuthorship W2953035981A5033047776 @default.
• W2953035981 hasAuthorship W2953035981A5035927942 @default.
• W2953035981 hasAuthorship W2953035981A5054455207 @default.
• W2953035981 hasAuthorship W2953035981A5075012459 @default.
• W2953035981 hasAuthorship W2953035981A5090151187 @default.
• W2953035981 hasBestOaLocation W29530359811 @default.
• W2953035981 hasConcept C111472728 @default.
• W2953035981 hasConcept C11413529 @default.
• W2953035981 hasConcept C115961682 @default.
• W2953035981 hasConcept C118615104 @default.
• W2953035981 hasConcept C121332964 @default.
• W2953035981 hasConcept C137293760 @default.
• W2953035981 hasConcept C138885662 @default.
• W2953035981 hasConcept C154945302 @default.
• W2953035981 hasConcept C163258240 @default.
• W2953035981 hasConcept C204321447 @default.
• W2953035981 hasConcept C2778112365 @default.
• W2953035981 hasConcept C2779462738 @default.
• W2953035981 hasConcept C2780069185 @default.
• W2953035981 hasConcept C2780586882 @default.
• W2953035981 hasConcept C2780992000 @default.
• W2953035981 hasConcept C2911011789 @default.
• W2953035981 hasConcept C33923547 @default.
• W2953035981 hasConcept C41008148 @default.
• W2953035981 hasConcept C50644808 @default.
• W2953035981 hasConcept C54355233 @default.
• W2953035981 hasConcept C55439883 @default.
• W2953035981 hasConcept C62520636 @default.
• W2953035981 hasConcept C86803240 @default.
• W2953035981 hasConcept C99498987 @default.
• W2953035981 hasConceptScore W2953035981C111472728 @default.
• W2953035981 hasConceptScore W2953035981C11413529 @default.
• W2953035981 hasConceptScore W2953035981C115961682 @default.
• W2953035981 hasConceptScore W2953035981C118615104 @default.
• W2953035981 hasConceptScore W2953035981C121332964 @default.
• W2953035981 hasConceptScore W2953035981C137293760 @default.
• W2953035981 hasConceptScore W2953035981C138885662 @default.
• W2953035981 hasConceptScore W2953035981C154945302 @default.
• W2953035981 hasConceptScore W2953035981C163258240 @default.
• W2953035981 hasConceptScore W2953035981C204321447 @default.
• W2953035981 hasConceptScore W2953035981C2778112365 @default.
• W2953035981 hasConceptScore W2953035981C2779462738 @default.
• W2953035981 hasConceptScore W2953035981C2780069185 @default.
• W2953035981 hasConceptScore W2953035981C2780586882 @default.
• W2953035981 hasConceptScore W2953035981C2780992000 @default.
• W2953035981 hasConceptScore W2953035981C2911011789 @default.
• W2953035981 hasConceptScore W2953035981C33923547 @default.
• W2953035981 hasConceptScore W2953035981C41008148 @default.
• W2953035981 hasConceptScore W2953035981C50644808 @default.
• W2953035981 hasConceptScore W2953035981C54355233 @default.
• W2953035981 hasConceptScore W2953035981C55439883 @default.
• W2953035981 hasConceptScore W2953035981C62520636 @default.
• W2953035981 hasConceptScore W2953035981C86803240 @default.
• W2953035981 hasConceptScore W2953035981C99498987 @default.
• W2953035981 hasLocation W29530359811 @default.
• W2953035981 hasOpenAccess W2953035981 @default.
• W2953035981 hasPrimaryLocation W29530359811 @default.
• W2953035981 hasRelatedWork W1517743118 @default.
• W2953035981 hasRelatedWork W1563618553 @default.
• W2953035981 hasRelatedWork W2026381003 @default.

• next