Matches in SemOpenAlex for { <https://semopenalex.org/work/W3017357710> ?p ?o ?g. }
- W3017357710 abstract "Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider multiple sources. Using an unrelated source can result in sub-optimal performance, known as the emph{negative transfer}. However, it is challenging to select the appropriate source(s) for classifying a given target instance in multi-source unsupervised domain adaptation (UDA). We model source-selection as an attention-learning problem, where we learn attention over sources for a given target instance. For this purpose, we first independently learn source-specific classification models, and a relatedness map between sources and target domains using pseudo-labelled target domain instances. Next, we learn attention-weights over the sources for aggregating the predictions of the source-specific models. Experimental results on cross-domain sentiment classification benchmarks show that the proposed method outperforms prior proposals in multi-source UDA." @default.
- W3017357710 created "2020-04-24" @default.
- W3017357710 creator A5065374968 @default.
- W3017357710 creator A5073503574 @default.
- W3017357710 date "2020-04-14" @default.
- W3017357710 modified "2023-09-24" @default.
- W3017357710 title "Multi-source Attention for Unsupervised Domain Adaptation." @default.
- W3017357710 cites W122553268 @default.
- W3017357710 cites W1533861849 @default.
- W3017357710 cites W1597032530 @default.
- W3017357710 cites W1731081199 @default.
- W3017357710 cites W1793121960 @default.
- W3017357710 cites W1980084379 @default.
- W3017357710 cites W2095579012 @default.
- W3017357710 cites W2096873754 @default.
- W3017357710 cites W2104094955 @default.
- W3017357710 cites W2120587290 @default.
- W3017357710 cites W2123160630 @default.
- W3017357710 cites W2131953535 @default.
- W3017357710 cites W2133458109 @default.
- W3017357710 cites W2133556223 @default.
- W3017357710 cites W2140398982 @default.
- W3017357710 cites W2153353890 @default.
- W3017357710 cites W2158108973 @default.
- W3017357710 cites W2163302275 @default.
- W3017357710 cites W2164943005 @default.
- W3017357710 cites W2165698076 @default.
- W3017357710 cites W2250539671 @default.
- W3017357710 cites W22861983 @default.
- W3017357710 cites W2507974895 @default.
- W3017357710 cites W2514769532 @default.
- W3017357710 cites W2735735104 @default.
- W3017357710 cites W2741239878 @default.
- W3017357710 cites W2741989495 @default.
- W3017357710 cites W2752172973 @default.
- W3017357710 cites W2777832646 @default.
- W3017357710 cites W2889406305 @default.
- W3017357710 cites W2891691791 @default.
- W3017357710 cites W2891745105 @default.
- W3017357710 cites W2891975605 @default.
- W3017357710 cites W2920890733 @default.
- W3017357710 cites W2949821452 @default.
- W3017357710 cites W2963326042 @default.
- W3017357710 cites W2964121744 @default.
- W3017357710 cites W2970641574 @default.
- W3017357710 cites W2998172865 @default.
- W3017357710 cites W3035219538 @default.
- W3017357710 cites W879220392 @default.
- W3017357710 hasPublicationYear "2020" @default.
- W3017357710 type Work @default.
- W3017357710 sameAs 3017357710 @default.
- W3017357710 citedByCount "1" @default.
- W3017357710 countsByYear W30173577102020 @default.
- W3017357710 crossrefType "posted-content" @default.
- W3017357710 hasAuthorship W3017357710A5065374968 @default.
- W3017357710 hasAuthorship W3017357710A5073503574 @default.
- W3017357710 hasConcept C105795698 @default.
- W3017357710 hasConcept C111110010 @default.
- W3017357710 hasConcept C112680207 @default.
- W3017357710 hasConcept C119857082 @default.
- W3017357710 hasConcept C120665830 @default.
- W3017357710 hasConcept C121332964 @default.
- W3017357710 hasConcept C124101348 @default.
- W3017357710 hasConcept C134306372 @default.
- W3017357710 hasConcept C139807058 @default.
- W3017357710 hasConcept C150899416 @default.
- W3017357710 hasConcept C154945302 @default.
- W3017357710 hasConcept C157972887 @default.
- W3017357710 hasConcept C2524010 @default.
- W3017357710 hasConcept C2776434776 @default.
- W3017357710 hasConcept C2780665216 @default.
- W3017357710 hasConcept C33923547 @default.
- W3017357710 hasConcept C36503486 @default.
- W3017357710 hasConcept C41008148 @default.
- W3017357710 hasConcept C58385900 @default.
- W3017357710 hasConcept C81917197 @default.
- W3017357710 hasConcept C95623464 @default.
- W3017357710 hasConceptScore W3017357710C105795698 @default.
- W3017357710 hasConceptScore W3017357710C111110010 @default.
- W3017357710 hasConceptScore W3017357710C112680207 @default.
- W3017357710 hasConceptScore W3017357710C119857082 @default.
- W3017357710 hasConceptScore W3017357710C120665830 @default.
- W3017357710 hasConceptScore W3017357710C121332964 @default.
- W3017357710 hasConceptScore W3017357710C124101348 @default.
- W3017357710 hasConceptScore W3017357710C134306372 @default.
- W3017357710 hasConceptScore W3017357710C139807058 @default.
- W3017357710 hasConceptScore W3017357710C150899416 @default.
- W3017357710 hasConceptScore W3017357710C154945302 @default.
- W3017357710 hasConceptScore W3017357710C157972887 @default.
- W3017357710 hasConceptScore W3017357710C2524010 @default.
- W3017357710 hasConceptScore W3017357710C2776434776 @default.
- W3017357710 hasConceptScore W3017357710C2780665216 @default.
- W3017357710 hasConceptScore W3017357710C33923547 @default.
- W3017357710 hasConceptScore W3017357710C36503486 @default.
- W3017357710 hasConceptScore W3017357710C41008148 @default.
- W3017357710 hasConceptScore W3017357710C58385900 @default.
- W3017357710 hasConceptScore W3017357710C81917197 @default.
- W3017357710 hasConceptScore W3017357710C95623464 @default.
- W3017357710 hasLocation W30173577101 @default.
- W3017357710 hasOpenAccess W3017357710 @default.