Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010705931> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3010705931 endingPage "41" @default.
- W3010705931 startingPage "36" @default.
- W3010705931 abstract "Coherence is a distinctive feature in well-written documents. One method to study coherence is to analyze how sentences are ordered in a document. In Multi-document Summarization, sentences from different sources need to be ordered. Cluster-based ordering algorithms aim to study various themes or topics that are present in a set of sentences. After the clusters of sentences have been identified, sentences are ordered within each cluster in isolation. One challenge that remains is to order these clusters or paragraphs to obtain a coherent ordering of information. Inspired by the success of deep neural networks in several NLP tasks, we propose an RNN-based encoder-decoder system to predict order for a given set of loose clusters or paragraphs. Universal Sentence Encoder (USE) is used to encode paragraphs into high dimensional embeddings, which are then fed into an LSTM encoder and consecutively passed to a pointer network, which finally outputs the paragraph order. Since Wikipedia is a source of well- structured articles, it is used to generate multiple datasets. Based on our experimental results, the proposed model satisfactorily outperforms the baseline model across multiple datasets. We observe a two-fold increase in Kendall's tau values for the final paragraph orderings." @default.
- W3010705931 created "2020-03-23" @default.
- W3010705931 creator A5026312063 @default.
- W3010705931 creator A5077159741 @default.
- W3010705931 date "2020-06-01" @default.
- W3010705931 modified "2023-09-30" @default.
- W3010705931 title "Modeling coherence by ordering paragraphs using pointer networks" @default.
- W3010705931 cites W2043849363 @default.
- W3010705931 cites W2064675550 @default.
- W3010705931 cites W2110568314 @default.
- W3010705931 cites W2125814131 @default.
- W3010705931 cites W2140676672 @default.
- W3010705931 cites W2148374900 @default.
- W3010705931 cites W2160992478 @default.
- W3010705931 cites W2776762669 @default.
- W3010705931 doi "https://doi.org/10.1016/j.neunet.2020.02.022" @default.
- W3010705931 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32179392" @default.
- W3010705931 hasPublicationYear "2020" @default.
- W3010705931 type Work @default.
- W3010705931 sameAs 3010705931 @default.
- W3010705931 citedByCount "4" @default.
- W3010705931 countsByYear W30107059312021 @default.
- W3010705931 countsByYear W30107059312022 @default.
- W3010705931 countsByYear W30107059312023 @default.
- W3010705931 crossrefType "journal-article" @default.
- W3010705931 hasAuthorship W3010705931A5026312063 @default.
- W3010705931 hasAuthorship W3010705931A5077159741 @default.
- W3010705931 hasConcept C104317684 @default.
- W3010705931 hasConcept C105795698 @default.
- W3010705931 hasConcept C111919701 @default.
- W3010705931 hasConcept C118505674 @default.
- W3010705931 hasConcept C136764020 @default.
- W3010705931 hasConcept C150202949 @default.
- W3010705931 hasConcept C153180895 @default.
- W3010705931 hasConcept C154945302 @default.
- W3010705931 hasConcept C170858558 @default.
- W3010705931 hasConcept C177264268 @default.
- W3010705931 hasConcept C185592680 @default.
- W3010705931 hasConcept C199360897 @default.
- W3010705931 hasConcept C204321447 @default.
- W3010705931 hasConcept C2777206241 @default.
- W3010705931 hasConcept C2777530160 @default.
- W3010705931 hasConcept C2781181686 @default.
- W3010705931 hasConcept C33923547 @default.
- W3010705931 hasConcept C41008148 @default.
- W3010705931 hasConcept C55493867 @default.
- W3010705931 hasConcept C66746571 @default.
- W3010705931 hasConceptScore W3010705931C104317684 @default.
- W3010705931 hasConceptScore W3010705931C105795698 @default.
- W3010705931 hasConceptScore W3010705931C111919701 @default.
- W3010705931 hasConceptScore W3010705931C118505674 @default.
- W3010705931 hasConceptScore W3010705931C136764020 @default.
- W3010705931 hasConceptScore W3010705931C150202949 @default.
- W3010705931 hasConceptScore W3010705931C153180895 @default.
- W3010705931 hasConceptScore W3010705931C154945302 @default.
- W3010705931 hasConceptScore W3010705931C170858558 @default.
- W3010705931 hasConceptScore W3010705931C177264268 @default.
- W3010705931 hasConceptScore W3010705931C185592680 @default.
- W3010705931 hasConceptScore W3010705931C199360897 @default.
- W3010705931 hasConceptScore W3010705931C204321447 @default.
- W3010705931 hasConceptScore W3010705931C2777206241 @default.
- W3010705931 hasConceptScore W3010705931C2777530160 @default.
- W3010705931 hasConceptScore W3010705931C2781181686 @default.
- W3010705931 hasConceptScore W3010705931C33923547 @default.
- W3010705931 hasConceptScore W3010705931C41008148 @default.
- W3010705931 hasConceptScore W3010705931C55493867 @default.
- W3010705931 hasConceptScore W3010705931C66746571 @default.
- W3010705931 hasLocation W30107059311 @default.
- W3010705931 hasLocation W30107059312 @default.
- W3010705931 hasOpenAccess W3010705931 @default.
- W3010705931 hasPrimaryLocation W30107059311 @default.
- W3010705931 hasRelatedWork W2275988210 @default.
- W3010705931 hasRelatedWork W2589098947 @default.
- W3010705931 hasRelatedWork W2609482285 @default.
- W3010705931 hasRelatedWork W2887112617 @default.
- W3010705931 hasRelatedWork W2942625049 @default.
- W3010705931 hasRelatedWork W2975809050 @default.
- W3010705931 hasRelatedWork W3007164922 @default.
- W3010705931 hasRelatedWork W3126935783 @default.
- W3010705931 hasRelatedWork W4225361096 @default.
- W3010705931 hasRelatedWork W49394845 @default.
- W3010705931 hasVolume "126" @default.
- W3010705931 isParatext "false" @default.
- W3010705931 isRetracted "false" @default.
- W3010705931 magId "3010705931" @default.
- W3010705931 workType "article" @default.