Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385222011> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4385222011 endingPage "8478" @default.
- W4385222011 startingPage "8478" @default.
- W4385222011 abstract "Neural models are widely applied to headline generation. Template-based methods are a promising direction to overcome the shortcomings of the neural headline generation (NHG) model in generating duplicate or extra words. Previous works often retrieve relevant headlines from the training data and adopt them as the soft template to guide the NHG model. However, these works had two drawbacks: reliance on additional retrieval tools, and uncertainty regarding semantic consistency between the retrieved headline and the source article. The NHG model uncertainty can be utilized to generate hypotheses. The hypotheses generated based on a well-trained NHG model not only contain salient information but also exhibit diversity, making them suitable as soft templates. In this study, we use a basic NHG model to generate multiple diverse hypotheses as candidate templates. Then, we propose a novel Multiple-Hypotheses-based NHG (MH-NHG) model. Experiments on English headline generation tasks demonstrate that it outperforms several baseline systems and achieves a comparable performance with the state-of-the-art system. This indicates that MH-NHG can generate more accurate headlines guided by multiple hypotheses." @default.
- W4385222011 created "2023-07-25" @default.
- W4385222011 creator A5058664733 @default.
- W4385222011 creator A5070196864 @default.
- W4385222011 creator A5074992749 @default.
- W4385222011 creator A5079950645 @default.
- W4385222011 date "2023-07-22" @default.
- W4385222011 modified "2023-10-16" @default.
- W4385222011 title "Incorporating Multi-Hypotheses as Soft-Templates in Neural Headline Generation" @default.
- W4385222011 cites W1566289585 @default.
- W4385222011 cites W2467173223 @default.
- W4385222011 cites W2526471240 @default.
- W4385222011 cites W2557480356 @default.
- W4385222011 cites W2735492478 @default.
- W4385222011 cites W2768957049 @default.
- W4385222011 cites W2798542795 @default.
- W4385222011 cites W2962739339 @default.
- W4385222011 cites W2962944953 @default.
- W4385222011 cites W2962965405 @default.
- W4385222011 cites W2962974924 @default.
- W4385222011 cites W2963104691 @default.
- W4385222011 cites W2963463964 @default.
- W4385222011 cites W2963807318 @default.
- W4385222011 cites W2964165364 @default.
- W4385222011 cites W2971302374 @default.
- W4385222011 cites W3034325332 @default.
- W4385222011 cites W3034999214 @default.
- W4385222011 cites W3104486441 @default.
- W4385222011 cites W3167739156 @default.
- W4385222011 cites W3168839501 @default.
- W4385222011 cites W3172044616 @default.
- W4385222011 cites W3175689281 @default.
- W4385222011 cites W3177224328 @default.
- W4385222011 cites W3198757395 @default.
- W4385222011 cites W3213394935 @default.
- W4385222011 doi "https://doi.org/10.3390/app13148478" @default.
- W4385222011 hasPublicationYear "2023" @default.
- W4385222011 type Work @default.
- W4385222011 citedByCount "0" @default.
- W4385222011 crossrefType "journal-article" @default.
- W4385222011 hasAuthorship W4385222011A5058664733 @default.
- W4385222011 hasAuthorship W4385222011A5070196864 @default.
- W4385222011 hasAuthorship W4385222011A5074992749 @default.
- W4385222011 hasAuthorship W4385222011A5079950645 @default.
- W4385222011 hasBestOaLocation W43852220111 @default.
- W4385222011 hasConcept C119857082 @default.
- W4385222011 hasConcept C138885662 @default.
- W4385222011 hasConcept C154945302 @default.
- W4385222011 hasConcept C199360897 @default.
- W4385222011 hasConcept C204321447 @default.
- W4385222011 hasConcept C2776436953 @default.
- W4385222011 hasConcept C2778689934 @default.
- W4385222011 hasConcept C41008148 @default.
- W4385222011 hasConcept C41895202 @default.
- W4385222011 hasConcept C82714645 @default.
- W4385222011 hasConceptScore W4385222011C119857082 @default.
- W4385222011 hasConceptScore W4385222011C138885662 @default.
- W4385222011 hasConceptScore W4385222011C154945302 @default.
- W4385222011 hasConceptScore W4385222011C199360897 @default.
- W4385222011 hasConceptScore W4385222011C204321447 @default.
- W4385222011 hasConceptScore W4385222011C2776436953 @default.
- W4385222011 hasConceptScore W4385222011C2778689934 @default.
- W4385222011 hasConceptScore W4385222011C41008148 @default.
- W4385222011 hasConceptScore W4385222011C41895202 @default.
- W4385222011 hasConceptScore W4385222011C82714645 @default.
- W4385222011 hasFunder F4320321001 @default.
- W4385222011 hasFunder F4320322868 @default.
- W4385222011 hasFunder F4320327830 @default.
- W4385222011 hasIssue "14" @default.
- W4385222011 hasLocation W43852220111 @default.
- W4385222011 hasLocation W43852220112 @default.
- W4385222011 hasOpenAccess W4385222011 @default.
- W4385222011 hasPrimaryLocation W43852220111 @default.
- W4385222011 hasRelatedWork W2353865532 @default.
- W4385222011 hasRelatedWork W2961085424 @default.
- W4385222011 hasRelatedWork W3046775127 @default.
- W4385222011 hasRelatedWork W3170094116 @default.
- W4385222011 hasRelatedWork W4205958290 @default.
- W4385222011 hasRelatedWork W4285260836 @default.
- W4385222011 hasRelatedWork W4286629047 @default.
- W4385222011 hasRelatedWork W4306321456 @default.
- W4385222011 hasRelatedWork W4306674287 @default.
- W4385222011 hasRelatedWork W4224009465 @default.
- W4385222011 hasVolume "13" @default.
- W4385222011 isParatext "false" @default.
- W4385222011 isRetracted "false" @default.
- W4385222011 workType "article" @default.