Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890738682> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2890738682 abstract "Traditional text classification methods make a basic assumption: the training and test data are homologous, while this naive assumption may not hold in the real world. Hence, this paper studies the problem of domain-adapted news text classification, hereby a model is trained on labeled data from one source domain and is able to be deployed on the other. To realize the cross-domain text classification, we propose a domain-adapted text classification method based on topic model LDA and TextCNN model, named TextLDACNN. Specifically, our work calculates the topic similarity between source and target domain, which is severed as an effective constraint to regularize the training process and hence improve the generalization of the source model to the target domain. Text classifier trained with unsupervised topic feature representation clearly outperforms the baseline TextCNN model. The result shows that our method achieves an approximately 4.0% improvement compared to the state-of-the-art method." @default.
- W2890738682 created "2018-09-27" @default.
- W2890738682 creator A5022636178 @default.
- W2890738682 creator A5024417199 @default.
- W2890738682 creator A5046206794 @default.
- W2890738682 creator A5083070890 @default.
- W2890738682 date "2018-08-17" @default.
- W2890738682 modified "2023-09-28" @default.
- W2890738682 title "Learning semantic topics for domain-adapted textual knowledge transfer" @default.
- W2890738682 cites W1487934831 @default.
- W2890738682 cites W1832693441 @default.
- W2890738682 cites W1880262756 @default.
- W2890738682 cites W1965963232 @default.
- W2890738682 cites W1972370969 @default.
- W2890738682 cites W1976529824 @default.
- W2890738682 cites W1992841082 @default.
- W2890738682 cites W2011261343 @default.
- W2890738682 cites W2044686187 @default.
- W2890738682 cites W2050103272 @default.
- W2890738682 cites W2063703901 @default.
- W2890738682 cites W2073792299 @default.
- W2890738682 cites W2097018403 @default.
- W2890738682 cites W2097774724 @default.
- W2890738682 cites W2130978632 @default.
- W2890738682 cites W2132481658 @default.
- W2890738682 cites W2165698076 @default.
- W2890738682 cites W2229332794 @default.
- W2890738682 cites W2294978630 @default.
- W2890738682 cites W2963168418 @default.
- W2890738682 doi "https://doi.org/10.1145/3240876.3240922" @default.
- W2890738682 hasPublicationYear "2018" @default.
- W2890738682 type Work @default.
- W2890738682 sameAs 2890738682 @default.
- W2890738682 citedByCount "0" @default.
- W2890738682 crossrefType "proceedings-article" @default.
- W2890738682 hasAuthorship W2890738682A5022636178 @default.
- W2890738682 hasAuthorship W2890738682A5024417199 @default.
- W2890738682 hasAuthorship W2890738682A5046206794 @default.
- W2890738682 hasAuthorship W2890738682A5083070890 @default.
- W2890738682 hasConcept C103278499 @default.
- W2890738682 hasConcept C115961682 @default.
- W2890738682 hasConcept C119857082 @default.
- W2890738682 hasConcept C134306372 @default.
- W2890738682 hasConcept C138885662 @default.
- W2890738682 hasConcept C150899416 @default.
- W2890738682 hasConcept C154945302 @default.
- W2890738682 hasConcept C16910744 @default.
- W2890738682 hasConcept C177148314 @default.
- W2890738682 hasConcept C199360897 @default.
- W2890738682 hasConcept C204321447 @default.
- W2890738682 hasConcept C23123220 @default.
- W2890738682 hasConcept C2524010 @default.
- W2890738682 hasConcept C2776036281 @default.
- W2890738682 hasConcept C2776145971 @default.
- W2890738682 hasConcept C2776401178 @default.
- W2890738682 hasConcept C33923547 @default.
- W2890738682 hasConcept C36503486 @default.
- W2890738682 hasConcept C41008148 @default.
- W2890738682 hasConcept C41895202 @default.
- W2890738682 hasConcept C51632099 @default.
- W2890738682 hasConcept C95623464 @default.
- W2890738682 hasConceptScore W2890738682C103278499 @default.
- W2890738682 hasConceptScore W2890738682C115961682 @default.
- W2890738682 hasConceptScore W2890738682C119857082 @default.
- W2890738682 hasConceptScore W2890738682C134306372 @default.
- W2890738682 hasConceptScore W2890738682C138885662 @default.
- W2890738682 hasConceptScore W2890738682C150899416 @default.
- W2890738682 hasConceptScore W2890738682C154945302 @default.
- W2890738682 hasConceptScore W2890738682C16910744 @default.
- W2890738682 hasConceptScore W2890738682C177148314 @default.
- W2890738682 hasConceptScore W2890738682C199360897 @default.
- W2890738682 hasConceptScore W2890738682C204321447 @default.
- W2890738682 hasConceptScore W2890738682C23123220 @default.
- W2890738682 hasConceptScore W2890738682C2524010 @default.
- W2890738682 hasConceptScore W2890738682C2776036281 @default.
- W2890738682 hasConceptScore W2890738682C2776145971 @default.
- W2890738682 hasConceptScore W2890738682C2776401178 @default.
- W2890738682 hasConceptScore W2890738682C33923547 @default.
- W2890738682 hasConceptScore W2890738682C36503486 @default.
- W2890738682 hasConceptScore W2890738682C41008148 @default.
- W2890738682 hasConceptScore W2890738682C41895202 @default.
- W2890738682 hasConceptScore W2890738682C51632099 @default.
- W2890738682 hasConceptScore W2890738682C95623464 @default.
- W2890738682 hasLocation W28907386821 @default.
- W2890738682 hasOpenAccess W2890738682 @default.
- W2890738682 hasPrimaryLocation W28907386821 @default.
- W2890738682 hasRelatedWork W10944326 @default.
- W2890738682 hasRelatedWork W2001391081 @default.
- W2890738682 hasRelatedWork W2059979378 @default.
- W2890738682 hasRelatedWork W2062518264 @default.
- W2890738682 hasRelatedWork W2146724556 @default.
- W2890738682 hasRelatedWork W2295948418 @default.
- W2890738682 hasRelatedWork W2769134059 @default.
- W2890738682 hasRelatedWork W2795384291 @default.
- W2890738682 hasRelatedWork W3042037165 @default.
- W2890738682 hasRelatedWork W4309048372 @default.
- W2890738682 isParatext "false" @default.
- W2890738682 isRetracted "false" @default.
- W2890738682 magId "2890738682" @default.
- W2890738682 workType "article" @default.