Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979478117> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2979478117 abstract "Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejadet al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on ConvAI2 dataset." @default.
- W2979478117 created "2019-10-18" @default.
- W2979478117 creator A5048500970 @default.
- W2979478117 creator A5068709817 @default.
- W2979478117 creator A5069665298 @default.
- W2979478117 creator A5087687501 @default.
- W2979478117 date "2019-01-01" @default.
- W2979478117 modified "2023-09-27" @default.
- W2979478117 title "DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks" @default.
- W2979478117 cites W10957333 @default.
- W2979478117 cites W1591706642 @default.
- W2979478117 cites W1793121960 @default.
- W2979478117 cites W1902237438 @default.
- W2979478117 cites W1956340063 @default.
- W2979478117 cites W2101105183 @default.
- W2979478117 cites W2108325777 @default.
- W2979478117 cites W2130942839 @default.
- W2979478117 cites W2157331557 @default.
- W2979478117 cites W2222949842 @default.
- W2979478117 cites W2402144811 @default.
- W2979478117 cites W2507756961 @default.
- W2979478117 cites W2586847566 @default.
- W2979478117 cites W2606974598 @default.
- W2979478117 cites W2741375528 @default.
- W2979478117 cites W2799176105 @default.
- W2979478117 cites W2885421725 @default.
- W2979478117 cites W2891958946 @default.
- W2979478117 cites W2962883855 @default.
- W2979478117 cites W2962965405 @default.
- W2979478117 cites W2963790827 @default.
- W2979478117 cites W2963871484 @default.
- W2979478117 cites W2963929190 @default.
- W2979478117 cites W2964121744 @default.
- W2979478117 cites W2964308564 @default.
- W2979478117 cites W2964352131 @default.
- W2979478117 doi "https://doi.org/10.18653/v1/w19-5917" @default.
- W2979478117 hasPublicationYear "2019" @default.
- W2979478117 type Work @default.
- W2979478117 sameAs 2979478117 @default.
- W2979478117 citedByCount "57" @default.
- W2979478117 countsByYear W29794781172019 @default.
- W2979478117 countsByYear W29794781172020 @default.
- W2979478117 countsByYear W29794781172021 @default.
- W2979478117 countsByYear W29794781172022 @default.
- W2979478117 countsByYear W29794781172023 @default.
- W2979478117 crossrefType "proceedings-article" @default.
- W2979478117 hasAuthorship W2979478117A5048500970 @default.
- W2979478117 hasAuthorship W2979478117A5068709817 @default.
- W2979478117 hasAuthorship W2979478117A5069665298 @default.
- W2979478117 hasAuthorship W2979478117A5087687501 @default.
- W2979478117 hasBestOaLocation W29794781171 @default.
- W2979478117 hasConcept C119857082 @default.
- W2979478117 hasConcept C137293760 @default.
- W2979478117 hasConcept C150202949 @default.
- W2979478117 hasConcept C151730666 @default.
- W2979478117 hasConcept C154945302 @default.
- W2979478117 hasConcept C170858558 @default.
- W2979478117 hasConcept C203005215 @default.
- W2979478117 hasConcept C204321447 @default.
- W2979478117 hasConcept C2779343474 @default.
- W2979478117 hasConcept C41008148 @default.
- W2979478117 hasConcept C50644808 @default.
- W2979478117 hasConcept C86803240 @default.
- W2979478117 hasConceptScore W2979478117C119857082 @default.
- W2979478117 hasConceptScore W2979478117C137293760 @default.
- W2979478117 hasConceptScore W2979478117C150202949 @default.
- W2979478117 hasConceptScore W2979478117C151730666 @default.
- W2979478117 hasConceptScore W2979478117C154945302 @default.
- W2979478117 hasConceptScore W2979478117C170858558 @default.
- W2979478117 hasConceptScore W2979478117C203005215 @default.
- W2979478117 hasConceptScore W2979478117C204321447 @default.
- W2979478117 hasConceptScore W2979478117C2779343474 @default.
- W2979478117 hasConceptScore W2979478117C41008148 @default.
- W2979478117 hasConceptScore W2979478117C50644808 @default.
- W2979478117 hasConceptScore W2979478117C86803240 @default.
- W2979478117 hasLocation W29794781171 @default.
- W2979478117 hasLocation W29794781172 @default.
- W2979478117 hasOpenAccess W2979478117 @default.
- W2979478117 hasPrimaryLocation W29794781171 @default.
- W2979478117 hasRelatedWork W2058999950 @default.
- W2979478117 hasRelatedWork W2129683077 @default.
- W2979478117 hasRelatedWork W2887112617 @default.
- W2979478117 hasRelatedWork W4226126415 @default.
- W2979478117 hasRelatedWork W4281385036 @default.
- W2979478117 hasRelatedWork W4284703357 @default.
- W2979478117 hasRelatedWork W4287887250 @default.
- W2979478117 hasRelatedWork W4360585598 @default.
- W2979478117 hasRelatedWork W4361804203 @default.
- W2979478117 hasRelatedWork W2610387714 @default.
- W2979478117 isParatext "false" @default.
- W2979478117 isRetracted "false" @default.
- W2979478117 magId "2979478117" @default.
- W2979478117 workType "article" @default.