Matches in SemOpenAlex for { <https://semopenalex.org/work/W2807812142> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2807812142 abstract "Sentence representation is one of the foundational tasks in natural language processing, and long short term memory (LSTM) is a widely used tool to deal with the variable-length sentence. In this paper, a new LSTM-based sentence representation model is proposed for sentence classification task. By introducing a self-supervised method in the process of learning the hidden representation of the sentence, the proposed model automatically capture the syntactic and semantic information from the context and used as additional language information to learn better contextual hidden representation. Moreover, instead of using the final hidden representation of LSTM or the max (or average) pooling of the hidden representations over all the time step, we propose to generate the global representation of the sentence by combining all contextual hidden representations in an element-wise attention manner. We evaluate our model on three sentence classification tasks: sentiment classification, question type classification, and subjectivity classification. Experimental results show that the proposed model improves the accuracy of sentence classification compared to other sentence representation methods in all of the three tasks." @default.
- W2807812142 created "2018-06-21" @default.
- W2807812142 creator A5052955491 @default.
- W2807812142 creator A5059469194 @default.
- W2807812142 creator A5064427024 @default.
- W2807812142 date "2018-03-01" @default.
- W2807812142 modified "2023-09-27" @default.
- W2807812142 title "Sentence representation and classification using attention and additional language information" @default.
- W2807812142 cites W1784932861 @default.
- W2807812142 cites W1832693441 @default.
- W2807812142 cites W1889268436 @default.
- W2807812142 cites W1902237438 @default.
- W2807812142 cites W1994598897 @default.
- W2807812142 cites W2064675550 @default.
- W2807812142 cites W2070246124 @default.
- W2807812142 cites W2114524997 @default.
- W2807812142 cites W2132339004 @default.
- W2807812142 cites W2154359981 @default.
- W2807812142 cites W2163455955 @default.
- W2807812142 cites W2251939518 @default.
- W2807812142 cites W2252215182 @default.
- W2807812142 cites W2327261103 @default.
- W2807812142 cites W2413794162 @default.
- W2807812142 cites W2462025561 @default.
- W2807812142 cites W2554720547 @default.
- W2807812142 cites W2597655663 @default.
- W2807812142 cites W2617855130 @default.
- W2807812142 cites W2682503061 @default.
- W2807812142 cites W2950577311 @default.
- W2807812142 cites W2962965405 @default.
- W2807812142 cites W2963355447 @default.
- W2807812142 cites W2964331270 @default.
- W2807812142 cites W71795751 @default.
- W2807812142 doi "https://doi.org/10.1109/icaci.2018.8377541" @default.
- W2807812142 hasPublicationYear "2018" @default.
- W2807812142 type Work @default.
- W2807812142 sameAs 2807812142 @default.
- W2807812142 citedByCount "1" @default.
- W2807812142 countsByYear W28078121422021 @default.
- W2807812142 crossrefType "proceedings-article" @default.
- W2807812142 hasAuthorship W2807812142A5052955491 @default.
- W2807812142 hasAuthorship W2807812142A5059469194 @default.
- W2807812142 hasAuthorship W2807812142A5064427024 @default.
- W2807812142 hasConcept C151730666 @default.
- W2807812142 hasConcept C154945302 @default.
- W2807812142 hasConcept C17744445 @default.
- W2807812142 hasConcept C199539241 @default.
- W2807812142 hasConcept C204321447 @default.
- W2807812142 hasConcept C2776359362 @default.
- W2807812142 hasConcept C2777530160 @default.
- W2807812142 hasConcept C2779343474 @default.
- W2807812142 hasConcept C41008148 @default.
- W2807812142 hasConcept C70437156 @default.
- W2807812142 hasConcept C86803240 @default.
- W2807812142 hasConcept C94625758 @default.
- W2807812142 hasConceptScore W2807812142C151730666 @default.
- W2807812142 hasConceptScore W2807812142C154945302 @default.
- W2807812142 hasConceptScore W2807812142C17744445 @default.
- W2807812142 hasConceptScore W2807812142C199539241 @default.
- W2807812142 hasConceptScore W2807812142C204321447 @default.
- W2807812142 hasConceptScore W2807812142C2776359362 @default.
- W2807812142 hasConceptScore W2807812142C2777530160 @default.
- W2807812142 hasConceptScore W2807812142C2779343474 @default.
- W2807812142 hasConceptScore W2807812142C41008148 @default.
- W2807812142 hasConceptScore W2807812142C70437156 @default.
- W2807812142 hasConceptScore W2807812142C86803240 @default.
- W2807812142 hasConceptScore W2807812142C94625758 @default.
- W2807812142 hasLocation W28078121421 @default.
- W2807812142 hasOpenAccess W2807812142 @default.
- W2807812142 hasPrimaryLocation W28078121421 @default.
- W2807812142 hasRelatedWork W2070811448 @default.
- W2807812142 hasRelatedWork W2503933322 @default.
- W2807812142 hasRelatedWork W2775543300 @default.
- W2807812142 hasRelatedWork W2789946045 @default.
- W2807812142 hasRelatedWork W2903529742 @default.
- W2807812142 hasRelatedWork W2906958571 @default.
- W2807812142 hasRelatedWork W2942173686 @default.
- W2807812142 hasRelatedWork W2945675118 @default.
- W2807812142 hasRelatedWork W2951514862 @default.
- W2807812142 hasRelatedWork W2953150860 @default.
- W2807812142 hasRelatedWork W2963053846 @default.
- W2807812142 hasRelatedWork W2963478142 @default.
- W2807812142 hasRelatedWork W2963644595 @default.
- W2807812142 hasRelatedWork W2970217403 @default.
- W2807812142 hasRelatedWork W3005282503 @default.
- W2807812142 hasRelatedWork W3092654696 @default.
- W2807812142 hasRelatedWork W3096299031 @default.
- W2807812142 hasRelatedWork W3098400973 @default.
- W2807812142 hasRelatedWork W3156854265 @default.
- W2807812142 hasRelatedWork W3199864557 @default.
- W2807812142 isParatext "false" @default.
- W2807812142 isRetracted "false" @default.
- W2807812142 magId "2807812142" @default.
- W2807812142 workType "article" @default.