Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895579464> ?p ?o ?g. }
- W2895579464 abstract "Multi-view learning can provide self-supervision when different views are available of the same data. Distributional hypothesis provides another form of useful self-supervision from adjacent sentences which are plentiful in large unlabelled corpora. Motivated by the asymmetry in the two hemispheres of the human brain as well as the observation that different learning architectures tend to emphasise different aspects of sentence meaning, we present two multi-view frameworks for learning sentence representations in an unsupervised fashion. One framework uses a generative objective and the other a discriminative one. In both frameworks, the final representation is an ensemble of two views, in which, one view encodes the input sentence with a Recurrent Neural Network (RNN), and the other view encodes it with a simple linear model. We show that, after learning, the vectors produced by our multi-view frameworks provide improved representations over their single-view learnt counterparts, and the combination of different views gives representational improvement over each view and demonstrates solid transferability on standard downstream tasks." @default.
- W2895579464 created "2018-10-12" @default.
- W2895579464 creator A5071129405 @default.
- W2895579464 creator A5078551585 @default.
- W2895579464 date "2018-09-27" @default.
- W2895579464 modified "2023-09-27" @default.
- W2895579464 title "Improving Sentence Representations with Multi-view Frameworks" @default.
- W2895579464 cites W1566289585 @default.
- W2895579464 cites W1615991656 @default.
- W2895579464 cites W1662133657 @default.
- W2895579464 cites W1677182931 @default.
- W2895579464 cites W1719619589 @default.
- W2895579464 cites W1814992895 @default.
- W2895579464 cites W1840435438 @default.
- W2895579464 cites W1883346539 @default.
- W2895579464 cites W1924770834 @default.
- W2895579464 cites W1980776243 @default.
- W2895579464 cites W2014902591 @default.
- W2895579464 cites W2027731328 @default.
- W2895579464 cites W2107795000 @default.
- W2895579464 cites W2114524997 @default.
- W2895579464 cites W2126400076 @default.
- W2895579464 cites W2129625650 @default.
- W2895579464 cites W2132598079 @default.
- W2895579464 cites W2133458109 @default.
- W2895579464 cites W2152180407 @default.
- W2895579464 cites W2153579005 @default.
- W2895579464 cites W2160660844 @default.
- W2895579464 cites W2163455955 @default.
- W2895579464 cites W2250539671 @default.
- W2895579464 cites W2250790822 @default.
- W2895579464 cites W2251291469 @default.
- W2895579464 cites W2251356693 @default.
- W2895579464 cites W2251861449 @default.
- W2895579464 cites W2251939518 @default.
- W2895579464 cites W2462305634 @default.
- W2895579464 cites W2493916176 @default.
- W2895579464 cites W2518186251 @default.
- W2895579464 cites W2610858497 @default.
- W2895579464 cites W2752172973 @default.
- W2895579464 cites W2761988601 @default.
- W2895579464 cites W2806042905 @default.
- W2895579464 cites W2882319491 @default.
- W2895579464 cites W2899771611 @default.
- W2895579464 cites W2949547296 @default.
- W2895579464 cites W2950726992 @default.
- W2895579464 cites W2950910987 @default.
- W2895579464 cites W2962772361 @default.
- W2895579464 cites W2963355447 @default.
- W2895579464 cites W2963644595 @default.
- W2895579464 cites W2963756346 @default.
- W2895579464 cites W2963804993 @default.
- W2895579464 cites W2963846996 @default.
- W2895579464 cites W2963918774 @default.
- W2895579464 cites W2964025273 @default.
- W2895579464 cites W2964165804 @default.
- W2895579464 cites W2964212550 @default.
- W2895579464 cites W2964294232 @default.
- W2895579464 cites W2964301648 @default.
- W2895579464 hasPublicationYear "2018" @default.
- W2895579464 type Work @default.
- W2895579464 sameAs 2895579464 @default.
- W2895579464 citedByCount "6" @default.
- W2895579464 countsByYear W28955794642019 @default.
- W2895579464 countsByYear W28955794642020 @default.
- W2895579464 crossrefType "posted-content" @default.
- W2895579464 hasAuthorship W2895579464A5071129405 @default.
- W2895579464 hasAuthorship W2895579464A5078551585 @default.
- W2895579464 hasConcept C119857082 @default.
- W2895579464 hasConcept C140331021 @default.
- W2895579464 hasConcept C154945302 @default.
- W2895579464 hasConcept C15744967 @default.
- W2895579464 hasConcept C167966045 @default.
- W2895579464 hasConcept C17744445 @default.
- W2895579464 hasConcept C199539241 @default.
- W2895579464 hasConcept C204321447 @default.
- W2895579464 hasConcept C2776359362 @default.
- W2895579464 hasConcept C2777530160 @default.
- W2895579464 hasConcept C2780876879 @default.
- W2895579464 hasConcept C39890363 @default.
- W2895579464 hasConcept C41008148 @default.
- W2895579464 hasConcept C542102704 @default.
- W2895579464 hasConcept C61272859 @default.
- W2895579464 hasConcept C94625758 @default.
- W2895579464 hasConcept C97931131 @default.
- W2895579464 hasConceptScore W2895579464C119857082 @default.
- W2895579464 hasConceptScore W2895579464C140331021 @default.
- W2895579464 hasConceptScore W2895579464C154945302 @default.
- W2895579464 hasConceptScore W2895579464C15744967 @default.
- W2895579464 hasConceptScore W2895579464C167966045 @default.
- W2895579464 hasConceptScore W2895579464C17744445 @default.
- W2895579464 hasConceptScore W2895579464C199539241 @default.
- W2895579464 hasConceptScore W2895579464C204321447 @default.
- W2895579464 hasConceptScore W2895579464C2776359362 @default.
- W2895579464 hasConceptScore W2895579464C2777530160 @default.
- W2895579464 hasConceptScore W2895579464C2780876879 @default.
- W2895579464 hasConceptScore W2895579464C39890363 @default.
- W2895579464 hasConceptScore W2895579464C41008148 @default.
- W2895579464 hasConceptScore W2895579464C542102704 @default.
- W2895579464 hasConceptScore W2895579464C61272859 @default.