Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081427626> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3081427626 endingPage "113898" @default.
- W3081427626 startingPage "113898" @default.
- W3081427626 abstract "Text classification, using deep learning techniques, has become a research challenge in natural language processing. Most of the existing deep learning models for text classification face difficulties when the length of the input text increases. Most models work well on shorter text inputs, however, their performance degrades with the increase in the input length. In this work, we introduce a model for text classification that can alleviate this problem. We present the hierarchical and lateral multiple timescales gated recurrent units (HL-MTGRU), in combination with pre-trained encoders to address the long text classification problem. HL-MTGRU can represent multiple temporal scale dependencies for the discrimination task. By combining the slow and fast units of the HL-MTGRU, our model effectively classifies long multi-sentence texts into the desired classes. We also show that the HL-MTGRU structure helps the model to prevent degradation of performance on longer text inputs. We demonstrate that the proposed network with the help of the latest pre-trained encoders for feature extraction outperforms the conventional models on various long text classification benchmark datasets." @default.
- W3081427626 created "2020-09-01" @default.
- W3081427626 creator A5016475473 @default.
- W3081427626 creator A5069774616 @default.
- W3081427626 date "2021-03-01" @default.
- W3081427626 modified "2023-10-17" @default.
- W3081427626 title "Hierarchical and lateral multiple timescales gated recurrent units with pre-trained encoder for long text classification" @default.
- W3081427626 cites W1978394996 @default.
- W3081427626 cites W1978579256 @default.
- W3081427626 cites W2028418738 @default.
- W3081427626 cites W2044275678 @default.
- W3081427626 cites W2064675550 @default.
- W3081427626 cites W2195506630 @default.
- W3081427626 cites W2250539671 @default.
- W3081427626 cites W2756946152 @default.
- W3081427626 cites W2998517938 @default.
- W3081427626 cites W4205184193 @default.
- W3081427626 cites W4205671217 @default.
- W3081427626 doi "https://doi.org/10.1016/j.eswa.2020.113898" @default.
- W3081427626 hasPublicationYear "2021" @default.
- W3081427626 type Work @default.
- W3081427626 sameAs 3081427626 @default.
- W3081427626 citedByCount "10" @default.
- W3081427626 countsByYear W30814276262021 @default.
- W3081427626 countsByYear W30814276262022 @default.
- W3081427626 countsByYear W30814276262023 @default.
- W3081427626 crossrefType "journal-article" @default.
- W3081427626 hasAuthorship W3081427626A5016475473 @default.
- W3081427626 hasAuthorship W3081427626A5069774616 @default.
- W3081427626 hasConcept C111919701 @default.
- W3081427626 hasConcept C118505674 @default.
- W3081427626 hasConcept C119857082 @default.
- W3081427626 hasConcept C13280743 @default.
- W3081427626 hasConcept C138885662 @default.
- W3081427626 hasConcept C147168706 @default.
- W3081427626 hasConcept C153180895 @default.
- W3081427626 hasConcept C154945302 @default.
- W3081427626 hasConcept C162324750 @default.
- W3081427626 hasConcept C185798385 @default.
- W3081427626 hasConcept C187736073 @default.
- W3081427626 hasConcept C204321447 @default.
- W3081427626 hasConcept C205649164 @default.
- W3081427626 hasConcept C2776401178 @default.
- W3081427626 hasConcept C2777530160 @default.
- W3081427626 hasConcept C2780451532 @default.
- W3081427626 hasConcept C41008148 @default.
- W3081427626 hasConcept C41895202 @default.
- W3081427626 hasConcept C50644808 @default.
- W3081427626 hasConceptScore W3081427626C111919701 @default.
- W3081427626 hasConceptScore W3081427626C118505674 @default.
- W3081427626 hasConceptScore W3081427626C119857082 @default.
- W3081427626 hasConceptScore W3081427626C13280743 @default.
- W3081427626 hasConceptScore W3081427626C138885662 @default.
- W3081427626 hasConceptScore W3081427626C147168706 @default.
- W3081427626 hasConceptScore W3081427626C153180895 @default.
- W3081427626 hasConceptScore W3081427626C154945302 @default.
- W3081427626 hasConceptScore W3081427626C162324750 @default.
- W3081427626 hasConceptScore W3081427626C185798385 @default.
- W3081427626 hasConceptScore W3081427626C187736073 @default.
- W3081427626 hasConceptScore W3081427626C204321447 @default.
- W3081427626 hasConceptScore W3081427626C205649164 @default.
- W3081427626 hasConceptScore W3081427626C2776401178 @default.
- W3081427626 hasConceptScore W3081427626C2777530160 @default.
- W3081427626 hasConceptScore W3081427626C2780451532 @default.
- W3081427626 hasConceptScore W3081427626C41008148 @default.
- W3081427626 hasConceptScore W3081427626C41895202 @default.
- W3081427626 hasConceptScore W3081427626C50644808 @default.
- W3081427626 hasFunder F4320321681 @default.
- W3081427626 hasFunder F4320335489 @default.
- W3081427626 hasLocation W30814276261 @default.
- W3081427626 hasOpenAccess W3081427626 @default.
- W3081427626 hasPrimaryLocation W30814276261 @default.
- W3081427626 hasRelatedWork W1567338489 @default.
- W3081427626 hasRelatedWork W159132833 @default.
- W3081427626 hasRelatedWork W1978971213 @default.
- W3081427626 hasRelatedWork W2081647779 @default.
- W3081427626 hasRelatedWork W2886197491 @default.
- W3081427626 hasRelatedWork W2887799774 @default.
- W3081427626 hasRelatedWork W2889111319 @default.
- W3081427626 hasRelatedWork W3107474891 @default.
- W3081427626 hasRelatedWork W3185852197 @default.
- W3081427626 hasRelatedWork W38394648 @default.
- W3081427626 hasVolume "165" @default.
- W3081427626 isParatext "false" @default.
- W3081427626 isRetracted "false" @default.
- W3081427626 magId "3081427626" @default.
- W3081427626 workType "article" @default.