Matches in SemOpenAlex for { <https://semopenalex.org/work/W2573425638> ?p ?o ?g. }
- W2573425638 endingPage "2760" @default.
- W2573425638 startingPage "2754" @default.
- W2573425638 abstract "Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to help model larger spans of text, e.g., documents, is intriguing, and further investigation would still be desirable. This paper aims to enhance neural network models for such a purpose. A typical problem of document-level modeling is automatic summarization, which aims to model documents in order to generate summaries. In this paper, we propose neural models to train computers not just to pay attention to specific regions and content of input documents with attention models, but also distract them to traverse between different content of a document so as to better grasp the overall meaning for summarization. Without engineering any features, we train the models on two large datasets. The models achieve the state-of-the-art performance, and they significantly benefit from the distraction modeling, particularly when input documents are long." @default.
- W2573425638 created "2017-01-26" @default.
- W2573425638 creator A5008456610 @default.
- W2573425638 creator A5016892586 @default.
- W2573425638 creator A5028771381 @default.
- W2573425638 creator A5050660824 @default.
- W2573425638 creator A5059767940 @default.
- W2573425638 date "2016-07-09" @default.
- W2573425638 modified "2023-09-23" @default.
- W2573425638 title "Distraction-based neural networks for modeling documents" @default.
- W2573425638 cites W1525595230 @default.
- W2573425638 cites W1544827683 @default.
- W2573425638 cites W1843891098 @default.
- W2573425638 cites W1879966306 @default.
- W2573425638 cites W1889268436 @default.
- W2573425638 cites W196214544 @default.
- W2573425638 cites W1974339500 @default.
- W2573425638 cites W1975579663 @default.
- W2573425638 cites W1989420837 @default.
- W2573425638 cites W2064675550 @default.
- W2573425638 cites W2076749833 @default.
- W2573425638 cites W2100664567 @default.
- W2573425638 cites W2104246439 @default.
- W2573425638 cites W2111369166 @default.
- W2573425638 cites W2120615054 @default.
- W2573425638 cites W2123442489 @default.
- W2573425638 cites W2125247927 @default.
- W2573425638 cites W2133564696 @default.
- W2573425638 cites W2143205289 @default.
- W2573425638 cites W2147489358 @default.
- W2573425638 cites W2151835172 @default.
- W2573425638 cites W2154652894 @default.
- W2573425638 cites W2158899491 @default.
- W2573425638 cites W2166347079 @default.
- W2573425638 cites W2191070669 @default.
- W2573425638 cites W2207587218 @default.
- W2573425638 cites W2218641061 @default.
- W2573425638 cites W2251387237 @default.
- W2573425638 cites W2251849926 @default.
- W2573425638 cites W2291126447 @default.
- W2573425638 cites W2949335953 @default.
- W2573425638 cites W2949888546 @default.
- W2573425638 cites W2950133940 @default.
- W2573425638 cites W2950635152 @default.
- W2573425638 cites W2950752421 @default.
- W2573425638 cites W2962996600 @default.
- W2573425638 cites W3151369355 @default.
- W2573425638 cites W6908809 @default.
- W2573425638 hasPublicationYear "2016" @default.
- W2573425638 type Work @default.
- W2573425638 sameAs 2573425638 @default.
- W2573425638 citedByCount "53" @default.
- W2573425638 countsByYear W25734256382016 @default.
- W2573425638 countsByYear W25734256382017 @default.
- W2573425638 countsByYear W25734256382018 @default.
- W2573425638 countsByYear W25734256382019 @default.
- W2573425638 countsByYear W25734256382020 @default.
- W2573425638 crossrefType "proceedings-article" @default.
- W2573425638 hasAuthorship W2573425638A5008456610 @default.
- W2573425638 hasAuthorship W2573425638A5016892586 @default.
- W2573425638 hasAuthorship W2573425638A5028771381 @default.
- W2573425638 hasAuthorship W2573425638A5050660824 @default.
- W2573425638 hasAuthorship W2573425638A5059767940 @default.
- W2573425638 hasConcept C119857082 @default.
- W2573425638 hasConcept C13280743 @default.
- W2573425638 hasConcept C154945302 @default.
- W2573425638 hasConcept C169760540 @default.
- W2573425638 hasConcept C170858558 @default.
- W2573425638 hasConcept C171268870 @default.
- W2573425638 hasConcept C176809094 @default.
- W2573425638 hasConcept C17744445 @default.
- W2573425638 hasConcept C199360897 @default.
- W2573425638 hasConcept C199539241 @default.
- W2573425638 hasConcept C204321447 @default.
- W2573425638 hasConcept C205649164 @default.
- W2573425638 hasConcept C23123220 @default.
- W2573425638 hasConcept C2776359362 @default.
- W2573425638 hasConcept C2776378700 @default.
- W2573425638 hasConcept C41008148 @default.
- W2573425638 hasConcept C50644808 @default.
- W2573425638 hasConcept C86803240 @default.
- W2573425638 hasConcept C94625758 @default.
- W2573425638 hasConceptScore W2573425638C119857082 @default.
- W2573425638 hasConceptScore W2573425638C13280743 @default.
- W2573425638 hasConceptScore W2573425638C154945302 @default.
- W2573425638 hasConceptScore W2573425638C169760540 @default.
- W2573425638 hasConceptScore W2573425638C170858558 @default.
- W2573425638 hasConceptScore W2573425638C171268870 @default.
- W2573425638 hasConceptScore W2573425638C176809094 @default.
- W2573425638 hasConceptScore W2573425638C17744445 @default.
- W2573425638 hasConceptScore W2573425638C199360897 @default.
- W2573425638 hasConceptScore W2573425638C199539241 @default.
- W2573425638 hasConceptScore W2573425638C204321447 @default.
- W2573425638 hasConceptScore W2573425638C205649164 @default.
- W2573425638 hasConceptScore W2573425638C23123220 @default.
- W2573425638 hasConceptScore W2573425638C2776359362 @default.
- W2573425638 hasConceptScore W2573425638C2776378700 @default.
- W2573425638 hasConceptScore W2573425638C41008148 @default.