Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298007906> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4298007906 endingPage "109948" @default.
- W4298007906 startingPage "109948" @default.
- W4298007906 abstract "A semantic extension-based classification algorithm for short texts, i.e., Set-CNN, is proposed in this paper. The proposed Set-CNN features three aspects. First, a semantic extension mechanism based on the fast clustering algorithm is applied to enrich the features of short texts. Second, a multiple-channel convolutional framework is proposed to capture semantic features at different levels. More specifically, both ordinary 1D convolution and atrous convolution are performed on the original texts to capture local and global semantic information. Ordinary 1D convolution convolves words one by one to capture original semantic information at the word level, which can be considered local semantic information. Atrous convolution convolves an entire short text to capture the context-level information of the original text, i.e., the global semantic information. This information can offset the noise incurred by semantic extension. The convolution channel equipped with an evolved GLU takes extended short texts as the object of convolution to capture semantic information at the extended context level. In addition, it functions to mitigate vanishing of the gradient. Third, we design a multiple-channel version of Text-CNN to generate different feature maps, which capture semantic features on different scales, and provide useful information to improve the classification performance of short texts. Finally, the performance of Set-CNN is assessed extensively over 4 datasets, namely, Subj, TREC, SST-2 and the Sogou corpus. The experimental results show that Set-CNN is more effective than state-of-the-art alternatives, including CNN-VE, multichannel CNN, BERT, etc. In particular, Set-CNN exhibits excellent performance as a lightweight text classifier, with lower computational complexity than BERTbase." @default.
- W4298007906 created "2022-10-01" @default.
- W4298007906 creator A5007897367 @default.
- W4298007906 creator A5054738516 @default.
- W4298007906 creator A5064756912 @default.
- W4298007906 creator A5069549198 @default.
- W4298007906 creator A5084610879 @default.
- W4298007906 date "2022-12-01" @default.
- W4298007906 modified "2023-10-12" @default.
- W4298007906 title "Set-CNN: A text convolutional neural network based on semantic extension for short text classification" @default.
- W4298007906 cites W1832693441 @default.
- W4298007906 cites W1960685374 @default.
- W4298007906 cites W1984762104 @default.
- W4298007906 cites W2031213082 @default.
- W4298007906 cites W2038021268 @default.
- W4298007906 cites W2064675550 @default.
- W4298007906 cites W2094728533 @default.
- W4298007906 cites W2110485445 @default.
- W4298007906 cites W2114544510 @default.
- W4298007906 cites W2118020653 @default.
- W4298007906 cites W2120615054 @default.
- W4298007906 cites W2168625136 @default.
- W4298007906 cites W2194775991 @default.
- W4298007906 cites W2250539671 @default.
- W4298007906 cites W2316377833 @default.
- W4298007906 cites W2340381866 @default.
- W4298007906 cites W2344975321 @default.
- W4298007906 cites W2514114770 @default.
- W4298007906 cites W2576754561 @default.
- W4298007906 cites W2618530766 @default.
- W4298007906 cites W2789354743 @default.
- W4298007906 cites W2888310236 @default.
- W4298007906 cites W2954311367 @default.
- W4298007906 cites W2963208026 @default.
- W4298007906 cites W2963477629 @default.
- W4298007906 cites W2995824694 @default.
- W4298007906 cites W2997200074 @default.
- W4298007906 cites W3014812975 @default.
- W4298007906 cites W3021155507 @default.
- W4298007906 cites W3032634577 @default.
- W4298007906 cites W3123091093 @default.
- W4298007906 cites W3119961356 @default.
- W4298007906 doi "https://doi.org/10.1016/j.knosys.2022.109948" @default.
- W4298007906 hasPublicationYear "2022" @default.
- W4298007906 type Work @default.
- W4298007906 citedByCount "13" @default.
- W4298007906 countsByYear W42980079062022 @default.
- W4298007906 countsByYear W42980079062023 @default.
- W4298007906 crossrefType "journal-article" @default.
- W4298007906 hasAuthorship W4298007906A5007897367 @default.
- W4298007906 hasAuthorship W4298007906A5054738516 @default.
- W4298007906 hasAuthorship W4298007906A5064756912 @default.
- W4298007906 hasAuthorship W4298007906A5069549198 @default.
- W4298007906 hasAuthorship W4298007906A5084610879 @default.
- W4298007906 hasConcept C153180895 @default.
- W4298007906 hasConcept C154945302 @default.
- W4298007906 hasConcept C177264268 @default.
- W4298007906 hasConcept C199360897 @default.
- W4298007906 hasConcept C204321447 @default.
- W4298007906 hasConcept C23123220 @default.
- W4298007906 hasConcept C2778029271 @default.
- W4298007906 hasConcept C41008148 @default.
- W4298007906 hasConcept C81363708 @default.
- W4298007906 hasConceptScore W4298007906C153180895 @default.
- W4298007906 hasConceptScore W4298007906C154945302 @default.
- W4298007906 hasConceptScore W4298007906C177264268 @default.
- W4298007906 hasConceptScore W4298007906C199360897 @default.
- W4298007906 hasConceptScore W4298007906C204321447 @default.
- W4298007906 hasConceptScore W4298007906C23123220 @default.
- W4298007906 hasConceptScore W4298007906C2778029271 @default.
- W4298007906 hasConceptScore W4298007906C41008148 @default.
- W4298007906 hasConceptScore W4298007906C81363708 @default.
- W4298007906 hasFunder F4320327912 @default.
- W4298007906 hasFunder F4320335777 @default.
- W4298007906 hasLocation W42980079061 @default.
- W4298007906 hasOpenAccess W4298007906 @default.
- W4298007906 hasPrimaryLocation W42980079061 @default.
- W4298007906 hasRelatedWork W1568049691 @default.
- W4298007906 hasRelatedWork W2075768550 @default.
- W4298007906 hasRelatedWork W2082716031 @default.
- W4298007906 hasRelatedWork W2321004070 @default.
- W4298007906 hasRelatedWork W2369178846 @default.
- W4298007906 hasRelatedWork W2370289839 @default.
- W4298007906 hasRelatedWork W2581850242 @default.
- W4298007906 hasRelatedWork W3022218857 @default.
- W4298007906 hasRelatedWork W4293226380 @default.
- W4298007906 hasRelatedWork W952723542 @default.
- W4298007906 hasVolume "257" @default.
- W4298007906 isParatext "false" @default.
- W4298007906 isRetracted "false" @default.
- W4298007906 workType "article" @default.