Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170687519> ?p ?o ?g. }
- W3170687519 abstract "This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys generic content, and the leaf sentences describe specific topics. Experimental results demonstrate that the generated topic sentences are appropriate as a summary of opinionated texts, which are more informative and cover more input contents than those generated by the recent unsupervised summarization model (Brav{z}inskas et al., 2020). Furthermore, we demonstrate that the variance of latent Gaussians represents the granularity of sentences, analogous to Gaussian word embedding (Vilnis and McCallum, 2015)." @default.
- W3170687519 created "2021-06-22" @default.
- W3170687519 creator A5014750522 @default.
- W3170687519 creator A5071470375 @default.
- W3170687519 creator A5073503574 @default.
- W3170687519 creator A5073805047 @default.
- W3170687519 date "2021-06-15" @default.
- W3170687519 modified "2023-09-25" @default.
- W3170687519 title "Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance" @default.
- W3170687519 cites W1522301498 @default.
- W3170687519 cites W1902237438 @default.
- W3170687519 cites W1924770834 @default.
- W3170687519 cites W1936155969 @default.
- W3170687519 cites W1939882552 @default.
- W3170687519 cites W1959608418 @default.
- W3170687519 cites W2003899488 @default.
- W3170687519 cites W2005564522 @default.
- W3170687519 cites W2027731328 @default.
- W3170687519 cites W2083305840 @default.
- W3170687519 cites W2105542801 @default.
- W3170687519 cites W2120543014 @default.
- W3170687519 cites W2132827946 @default.
- W3170687519 cites W2140676672 @default.
- W3170687519 cites W2148404145 @default.
- W3170687519 cites W2150869743 @default.
- W3170687519 cites W2154652894 @default.
- W3170687519 cites W2154970197 @default.
- W3170687519 cites W2250571530 @default.
- W3170687519 cites W2270627573 @default.
- W3170687519 cites W2548228487 @default.
- W3170687519 cites W2606974598 @default.
- W3170687519 cites W2757311323 @default.
- W3170687519 cites W2888507208 @default.
- W3170687519 cites W2890116189 @default.
- W3170687519 cites W2944931850 @default.
- W3170687519 cites W2950670227 @default.
- W3170687519 cites W2951897943 @default.
- W3170687519 cites W2955471745 @default.
- W3170687519 cites W2962755817 @default.
- W3170687519 cites W2962796133 @default.
- W3170687519 cites W2962897886 @default.
- W3170687519 cites W2963161084 @default.
- W3170687519 cites W2963223306 @default.
- W3170687519 cites W2963341956 @default.
- W3170687519 cites W2963456134 @default.
- W3170687519 cites W2963600562 @default.
- W3170687519 cites W2963929190 @default.
- W3170687519 cites W2964222296 @default.
- W3170687519 cites W2964235962 @default.
- W3170687519 cites W2970419734 @default.
- W3170687519 cites W2971106293 @default.
- W3170687519 cites W2996287690 @default.
- W3170687519 cites W2996428491 @default.
- W3170687519 cites W3017806159 @default.
- W3170687519 cites W3034383590 @default.
- W3170687519 cites W3034715004 @default.
- W3170687519 cites W3034735823 @default.
- W3170687519 cites W3035043191 @default.
- W3170687519 cites W3104033643 @default.
- W3170687519 cites W3112588582 @default.
- W3170687519 cites W3153621364 @default.
- W3170687519 cites W42510783 @default.
- W3170687519 doi "https://doi.org/10.48550/arxiv.2106.08007" @default.
- W3170687519 hasPublicationYear "2021" @default.
- W3170687519 type Work @default.
- W3170687519 sameAs 3170687519 @default.
- W3170687519 citedByCount "0" @default.
- W3170687519 crossrefType "posted-content" @default.
- W3170687519 hasAuthorship W3170687519A5014750522 @default.
- W3170687519 hasAuthorship W3170687519A5071470375 @default.
- W3170687519 hasAuthorship W3170687519A5073503574 @default.
- W3170687519 hasAuthorship W3170687519A5073805047 @default.
- W3170687519 hasBestOaLocation W31706875191 @default.
- W3170687519 hasConcept C101738243 @default.
- W3170687519 hasConcept C108583219 @default.
- W3170687519 hasConcept C113174947 @default.
- W3170687519 hasConcept C11413529 @default.
- W3170687519 hasConcept C121332964 @default.
- W3170687519 hasConcept C134306372 @default.
- W3170687519 hasConcept C138885662 @default.
- W3170687519 hasConcept C154945302 @default.
- W3170687519 hasConcept C163716315 @default.
- W3170687519 hasConcept C163797641 @default.
- W3170687519 hasConcept C168167062 @default.
- W3170687519 hasConcept C170858558 @default.
- W3170687519 hasConcept C171686336 @default.
- W3170687519 hasConcept C197855036 @default.
- W3170687519 hasConcept C204321447 @default.
- W3170687519 hasConcept C2777530160 @default.
- W3170687519 hasConcept C33923547 @default.
- W3170687519 hasConcept C41008148 @default.
- W3170687519 hasConcept C41895202 @default.
- W3170687519 hasConcept C57273362 @default.
- W3170687519 hasConcept C62520636 @default.
- W3170687519 hasConcept C90805587 @default.
- W3170687519 hasConcept C97355855 @default.
- W3170687519 hasConceptScore W3170687519C101738243 @default.
- W3170687519 hasConceptScore W3170687519C108583219 @default.
- W3170687519 hasConceptScore W3170687519C113174947 @default.
- W3170687519 hasConceptScore W3170687519C11413529 @default.