Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386487595> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4386487595 abstract "Retrieval-based dialogue systems have achieved great performance improvements after the raise of pre-trained language models and Transformer mechanisms. In the process of context and response selection, the pre-trained language model can capture the relationship between texts, but current existing methods don’t consider the order of sentences and the relationship between the context and the response. At the same time, as the problem of a small number of positive samples in retrieval-based dialogue systems, it is difficult to train a learning model with high performance. In addition, existing methods usually requires the larger computational cost after splicing the context and the response. To solve the above problems, we propose a post-encoding approach combining with the strategy of contrastive learning. The order of the context and the relationship between sentences in dialogues and response are reflected in the encoding process, and a new loss function is designed for contrastive learning. The propose approach is validated through experiments on public datasets. The experiment results show that our model achieves better performance and effectiveness compared to existing methods." @default.
- W4386487595 created "2023-09-07" @default.
- W4386487595 creator A5025084093 @default.
- W4386487595 creator A5028945309 @default.
- W4386487595 creator A5042908851 @default.
- W4386487595 creator A5081263592 @default.
- W4386487595 creator A5085829666 @default.
- W4386487595 date "2023-03-01" @default.
- W4386487595 modified "2023-09-27" @default.
- W4386487595 title "Post-encoding and contrastive learning method for response selection task" @default.
- W4386487595 cites W2798456655 @default.
- W4386487595 cites W2891416139 @default.
- W4386487595 cites W2952813980 @default.
- W4386487595 cites W2962854379 @default.
- W4386487595 cites W2970648534 @default.
- W4386487595 cites W3094612274 @default.
- W4386487595 doi "https://doi.org/10.1109/icnlp58431.2023.00050" @default.
- W4386487595 hasPublicationYear "2023" @default.
- W4386487595 type Work @default.
- W4386487595 citedByCount "0" @default.
- W4386487595 crossrefType "proceedings-article" @default.
- W4386487595 hasAuthorship W4386487595A5025084093 @default.
- W4386487595 hasAuthorship W4386487595A5028945309 @default.
- W4386487595 hasAuthorship W4386487595A5042908851 @default.
- W4386487595 hasAuthorship W4386487595A5081263592 @default.
- W4386487595 hasAuthorship W4386487595A5085829666 @default.
- W4386487595 hasConcept C111919701 @default.
- W4386487595 hasConcept C119857082 @default.
- W4386487595 hasConcept C121332964 @default.
- W4386487595 hasConcept C125411270 @default.
- W4386487595 hasConcept C137293760 @default.
- W4386487595 hasConcept C151730666 @default.
- W4386487595 hasConcept C154945302 @default.
- W4386487595 hasConcept C165801399 @default.
- W4386487595 hasConcept C204321447 @default.
- W4386487595 hasConcept C2779343474 @default.
- W4386487595 hasConcept C41008148 @default.
- W4386487595 hasConcept C62520636 @default.
- W4386487595 hasConcept C66322947 @default.
- W4386487595 hasConcept C81917197 @default.
- W4386487595 hasConcept C86803240 @default.
- W4386487595 hasConcept C98045186 @default.
- W4386487595 hasConceptScore W4386487595C111919701 @default.
- W4386487595 hasConceptScore W4386487595C119857082 @default.
- W4386487595 hasConceptScore W4386487595C121332964 @default.
- W4386487595 hasConceptScore W4386487595C125411270 @default.
- W4386487595 hasConceptScore W4386487595C137293760 @default.
- W4386487595 hasConceptScore W4386487595C151730666 @default.
- W4386487595 hasConceptScore W4386487595C154945302 @default.
- W4386487595 hasConceptScore W4386487595C165801399 @default.
- W4386487595 hasConceptScore W4386487595C204321447 @default.
- W4386487595 hasConceptScore W4386487595C2779343474 @default.
- W4386487595 hasConceptScore W4386487595C41008148 @default.
- W4386487595 hasConceptScore W4386487595C62520636 @default.
- W4386487595 hasConceptScore W4386487595C66322947 @default.
- W4386487595 hasConceptScore W4386487595C81917197 @default.
- W4386487595 hasConceptScore W4386487595C86803240 @default.
- W4386487595 hasConceptScore W4386487595C98045186 @default.
- W4386487595 hasLocation W43864875951 @default.
- W4386487595 hasOpenAccess W4386487595 @default.
- W4386487595 hasPrimaryLocation W43864875951 @default.
- W4386487595 hasRelatedWork W2250741237 @default.
- W4386487595 hasRelatedWork W2359001871 @default.
- W4386487595 hasRelatedWork W3008110149 @default.
- W4386487595 hasRelatedWork W3033862527 @default.
- W4386487595 hasRelatedWork W3033942572 @default.
- W4386487595 hasRelatedWork W3097571385 @default.
- W4386487595 hasRelatedWork W3196747313 @default.
- W4386487595 hasRelatedWork W4287761227 @default.
- W4386487595 hasRelatedWork W4316012698 @default.
- W4386487595 hasRelatedWork W4381786178 @default.
- W4386487595 isParatext "false" @default.
- W4386487595 isRetracted "false" @default.
- W4386487595 workType "article" @default.