Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100439863> ?p ?o ?g. }
- W3100439863 abstract "Much progress has been made in text summarization, fueled by neural architectures using large-scale training corpora. However, in the news domain, neural models easily overfit by leveraging position-related features due to the prevalence of the inverted pyramid writing style. In addition, there is an unmet need to generate a variety of summaries for different users. In this paper, we propose a neural framework that can flexibly control summary generation by introducing a set of sub-aspect functions (i.e. importance, diversity, position). These sub-aspect functions are regulated by a set of control codes to decide which sub-aspect to focus on during summary generation. We demonstrate that extracted summaries with minimal position bias is comparable with those generated by standard models that take advantage of position preference. We also show that news summaries generated with a focus on diversity can be more preferred by human raters. These results suggest that a more flexible neural summarization framework providing more control options could be desirable in tailoring to different user preferences, which is useful since it is often impractical to articulate such preferences for different applications a priori." @default.
- W3100439863 created "2020-11-23" @default.
- W3100439863 creator A5012351801 @default.
- W3100439863 creator A5014190404 @default.
- W3100439863 creator A5035806489 @default.
- W3100439863 date "2020-01-01" @default.
- W3100439863 modified "2023-09-24" @default.
- W3100439863 title "Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization" @default.
- W3100439863 cites W1504817511 @default.
- W3100439863 cites W1525595230 @default.
- W3100439863 cites W1544827683 @default.
- W3100439863 cites W1979068940 @default.
- W3100439863 cites W1995953117 @default.
- W3100439863 cites W2048207804 @default.
- W3100439863 cites W2055452728 @default.
- W3100439863 cites W2083305840 @default.
- W3100439863 cites W2095705004 @default.
- W3100439863 cites W2097440732 @default.
- W3100439863 cites W2101390659 @default.
- W3100439863 cites W2123946480 @default.
- W3100439863 cites W2125336414 @default.
- W3100439863 cites W2125389028 @default.
- W3100439863 cites W2131774270 @default.
- W3100439863 cites W2153504150 @default.
- W3100439863 cites W2154652894 @default.
- W3100439863 cites W2250483006 @default.
- W3100439863 cites W2270627573 @default.
- W3100439863 cites W2401044082 @default.
- W3100439863 cites W2574535369 @default.
- W3100439863 cites W2606974598 @default.
- W3100439863 cites W2753738274 @default.
- W3100439863 cites W2888482885 @default.
- W3100439863 cites W2889518897 @default.
- W3100439863 cites W2896807716 @default.
- W3100439863 cites W2951535825 @default.
- W3100439863 cites W2962917899 @default.
- W3100439863 cites W2962972512 @default.
- W3100439863 cites W2963035145 @default.
- W3100439863 cites W2963241965 @default.
- W3100439863 cites W2963341956 @default.
- W3100439863 cites W2963403868 @default.
- W3100439863 cites W2963607157 @default.
- W3100439863 cites W2964121744 @default.
- W3100439863 cites W2970419734 @default.
- W3100439863 cites W2971034336 @default.
- W3100439863 cites W2973049837 @default.
- W3100439863 cites W2988125365 @default.
- W3100439863 cites W2996403597 @default.
- W3100439863 cites W3088311774 @default.
- W3100439863 cites W3101913037 @default.
- W3100439863 cites W3158986179 @default.
- W3100439863 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.131" @default.
- W3100439863 hasPublicationYear "2020" @default.
- W3100439863 type Work @default.
- W3100439863 sameAs 3100439863 @default.
- W3100439863 citedByCount "3" @default.
- W3100439863 countsByYear W31004398632021 @default.
- W3100439863 crossrefType "proceedings-article" @default.
- W3100439863 hasAuthorship W3100439863A5012351801 @default.
- W3100439863 hasAuthorship W3100439863A5014190404 @default.
- W3100439863 hasAuthorship W3100439863A5035806489 @default.
- W3100439863 hasBestOaLocation W31004398631 @default.
- W3100439863 hasConcept C119857082 @default.
- W3100439863 hasConcept C120665830 @default.
- W3100439863 hasConcept C121332964 @default.
- W3100439863 hasConcept C154945302 @default.
- W3100439863 hasConcept C170858558 @default.
- W3100439863 hasConcept C177264268 @default.
- W3100439863 hasConcept C192209626 @default.
- W3100439863 hasConcept C199360897 @default.
- W3100439863 hasConcept C22019652 @default.
- W3100439863 hasConcept C23123220 @default.
- W3100439863 hasConcept C41008148 @default.
- W3100439863 hasConcept C50644808 @default.
- W3100439863 hasConceptScore W3100439863C119857082 @default.
- W3100439863 hasConceptScore W3100439863C120665830 @default.
- W3100439863 hasConceptScore W3100439863C121332964 @default.
- W3100439863 hasConceptScore W3100439863C154945302 @default.
- W3100439863 hasConceptScore W3100439863C170858558 @default.
- W3100439863 hasConceptScore W3100439863C177264268 @default.
- W3100439863 hasConceptScore W3100439863C192209626 @default.
- W3100439863 hasConceptScore W3100439863C199360897 @default.
- W3100439863 hasConceptScore W3100439863C22019652 @default.
- W3100439863 hasConceptScore W3100439863C23123220 @default.
- W3100439863 hasConceptScore W3100439863C41008148 @default.
- W3100439863 hasConceptScore W3100439863C50644808 @default.
- W3100439863 hasLocation W31004398631 @default.
- W3100439863 hasLocation W31004398632 @default.
- W3100439863 hasOpenAccess W3100439863 @default.
- W3100439863 hasPrimaryLocation W31004398631 @default.
- W3100439863 hasRelatedWork W11356396 @default.
- W3100439863 hasRelatedWork W12428677 @default.
- W3100439863 hasRelatedWork W234194 @default.
- W3100439863 hasRelatedWork W2371595 @default.
- W3100439863 hasRelatedWork W3901497 @default.
- W3100439863 hasRelatedWork W4771408 @default.
- W3100439863 hasRelatedWork W6264993 @default.
- W3100439863 hasRelatedWork W7339520 @default.
- W3100439863 hasRelatedWork W7973081 @default.
- W3100439863 hasRelatedWork W13002482 @default.