Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003932464> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3003932464 endingPage "76" @default.
- W3003932464 startingPage "67" @default.
- W3003932464 abstract "Despite the success of attention-based neural models for natural language generation and classification tasks, they are unable to capture the discourse structure of larger documents. We hypothesize that explicit discourse representations have utility for NLP tasks over longer documents or document sequences, which sequence-to-sequence models are unable to capture. For abstractive summarization, for instance, conventional neural models simply match source documents and the summary in a latent space without explicit representation of text structure or relations. In this paper, we propose to use neural discourse representations obtained from a rhetorical structure theory (RST) parser to enhance document representations. Specifically, document representations are generated for discourse spans, known as the elementary discourse units (EDUs). We empirically investigate the benefit of the proposed approach on two different tasks: abstractive summarization and popularity prediction of online petitions. We find that the proposed approach leads to substantial improvements in all cases." @default.
- W3003932464 created "2020-02-07" @default.
- W3003932464 creator A5032767467 @default.
- W3003932464 creator A5060332228 @default.
- W3003932464 creator A5065822589 @default.
- W3003932464 date "2019-11-16" @default.
- W3003932464 modified "2023-09-26" @default.
- W3003932464 title "Improved Document Modelling with a Neural Discourse Parser" @default.
- W3003932464 cites W2042128417 @default.
- W3003932464 cites W2045738181 @default.
- W3003932464 cites W2115242108 @default.
- W3003932464 cites W2154652894 @default.
- W3003932464 cites W2250539671 @default.
- W3003932464 cites W2250767751 @default.
- W3003932464 cites W2565349465 @default.
- W3003932464 cites W2604926689 @default.
- W3003932464 cites W2606974598 @default.
- W3003932464 cites W2778856544 @default.
- W3003932464 cites W2877801623 @default.
- W3003932464 cites W2962965405 @default.
- W3003932464 cites W2963029801 @default.
- W3003932464 cites W2963929190 @default.
- W3003932464 cites W2964308564 @default.
- W3003932464 cites W3088311774 @default.
- W3003932464 cites W2771344634 @default.
- W3003932464 hasPublicationYear "2019" @default.
- W3003932464 type Work @default.
- W3003932464 sameAs 3003932464 @default.
- W3003932464 citedByCount "4" @default.
- W3003932464 countsByYear W30039324642020 @default.
- W3003932464 countsByYear W30039324642021 @default.
- W3003932464 crossrefType "journal-article" @default.
- W3003932464 hasAuthorship W3003932464A5032767467 @default.
- W3003932464 hasAuthorship W3003932464A5060332228 @default.
- W3003932464 hasAuthorship W3003932464A5065822589 @default.
- W3003932464 hasConcept C138885662 @default.
- W3003932464 hasConcept C154945302 @default.
- W3003932464 hasConcept C170858558 @default.
- W3003932464 hasConcept C17744445 @default.
- W3003932464 hasConcept C186644900 @default.
- W3003932464 hasConcept C192562157 @default.
- W3003932464 hasConcept C195324797 @default.
- W3003932464 hasConcept C199539241 @default.
- W3003932464 hasConcept C204321447 @default.
- W3003932464 hasConcept C2776187449 @default.
- W3003932464 hasConcept C2776359362 @default.
- W3003932464 hasConcept C2778112365 @default.
- W3003932464 hasConcept C41008148 @default.
- W3003932464 hasConcept C41895202 @default.
- W3003932464 hasConcept C54355233 @default.
- W3003932464 hasConcept C86803240 @default.
- W3003932464 hasConcept C94625758 @default.
- W3003932464 hasConceptScore W3003932464C138885662 @default.
- W3003932464 hasConceptScore W3003932464C154945302 @default.
- W3003932464 hasConceptScore W3003932464C170858558 @default.
- W3003932464 hasConceptScore W3003932464C17744445 @default.
- W3003932464 hasConceptScore W3003932464C186644900 @default.
- W3003932464 hasConceptScore W3003932464C192562157 @default.
- W3003932464 hasConceptScore W3003932464C195324797 @default.
- W3003932464 hasConceptScore W3003932464C199539241 @default.
- W3003932464 hasConceptScore W3003932464C204321447 @default.
- W3003932464 hasConceptScore W3003932464C2776187449 @default.
- W3003932464 hasConceptScore W3003932464C2776359362 @default.
- W3003932464 hasConceptScore W3003932464C2778112365 @default.
- W3003932464 hasConceptScore W3003932464C41008148 @default.
- W3003932464 hasConceptScore W3003932464C41895202 @default.
- W3003932464 hasConceptScore W3003932464C54355233 @default.
- W3003932464 hasConceptScore W3003932464C86803240 @default.
- W3003932464 hasConceptScore W3003932464C94625758 @default.
- W3003932464 hasLocation W30039324641 @default.
- W3003932464 hasOpenAccess W3003932464 @default.
- W3003932464 hasPrimaryLocation W30039324641 @default.
- W3003932464 hasRelatedWork W2065140467 @default.
- W3003932464 hasRelatedWork W2074790252 @default.
- W3003932464 hasRelatedWork W2251013762 @default.
- W3003932464 hasRelatedWork W2297079992 @default.
- W3003932464 hasRelatedWork W2505232340 @default.
- W3003932464 hasRelatedWork W2556984224 @default.
- W3003932464 hasRelatedWork W2725426789 @default.
- W3003932464 hasRelatedWork W2761988601 @default.
- W3003932464 hasRelatedWork W2791431914 @default.
- W3003932464 hasRelatedWork W2806072203 @default.
- W3003932464 hasRelatedWork W2899406407 @default.
- W3003932464 hasRelatedWork W2944085222 @default.
- W3003932464 hasRelatedWork W2956000896 @default.
- W3003932464 hasRelatedWork W2962739339 @default.
- W3003932464 hasRelatedWork W2962932173 @default.
- W3003932464 hasRelatedWork W300214036 @default.
- W3003932464 hasRelatedWork W3093061433 @default.
- W3003932464 hasRelatedWork W3095760691 @default.
- W3003932464 hasRelatedWork W3111091152 @default.
- W3003932464 hasRelatedWork W3214691339 @default.
- W3003932464 isParatext "false" @default.
- W3003932464 isRetracted "false" @default.
- W3003932464 magId "3003932464" @default.
- W3003932464 workType "article" @default.