Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385574289> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4385574289 abstract "Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings remains a huge challenge for neural dialogue systems. To alleviate these problems, methods like introducing external information, reconstructing the optimization function, and manipulating data samples are proposed, while they primarily focus on avoiding training with CDM, inevitably weakening the model’s ability of understanding CDM in human conversations and limiting further improvements in model performance. This paper proposes a Sentence Semantic Segmentation guided Conditional Variational Auto-Encoder (SegCVAE) method which can model and take advantages of the CDM data. Specifically, to tackle the incoherent problem caused by one-to-many, SegCVAE uses response-related prominent semantics to constrained the latent variable. To mitigate the non-diverse problem brought by many-to-one, SegCVAE segments multiple prominent semantics to enrich the latent variables. Three novel components, Internal Separation, External Guidance, and Semantic Norms, are proposed to achieve SegCVAE. On dialogue generation tasks, both the automatic and human evaluation results show that SegCVAE achieves new state-of-the-art performance." @default.
- W4385574289 created "2023-08-05" @default.
- W4385574289 creator A5004624473 @default.
- W4385574289 creator A5012014905 @default.
- W4385574289 creator A5015941300 @default.
- W4385574289 creator A5016748416 @default.
- W4385574289 creator A5031477200 @default.
- W4385574289 creator A5059845740 @default.
- W4385574289 creator A5070683894 @default.
- W4385574289 date "2022-01-01" @default.
- W4385574289 modified "2023-10-16" @default.
- W4385574289 title "Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder" @default.
- W4385574289 doi "https://doi.org/10.18653/v1/2022.findings-emnlp.305" @default.
- W4385574289 hasPublicationYear "2022" @default.
- W4385574289 type Work @default.
- W4385574289 citedByCount "0" @default.
- W4385574289 crossrefType "proceedings-article" @default.
- W4385574289 hasAuthorship W4385574289A5004624473 @default.
- W4385574289 hasAuthorship W4385574289A5012014905 @default.
- W4385574289 hasAuthorship W4385574289A5015941300 @default.
- W4385574289 hasAuthorship W4385574289A5016748416 @default.
- W4385574289 hasAuthorship W4385574289A5031477200 @default.
- W4385574289 hasAuthorship W4385574289A5059845740 @default.
- W4385574289 hasAuthorship W4385574289A5070683894 @default.
- W4385574289 hasBestOaLocation W43855742891 @default.
- W4385574289 hasConcept C111919701 @default.
- W4385574289 hasConcept C118505674 @default.
- W4385574289 hasConcept C119857082 @default.
- W4385574289 hasConcept C120665830 @default.
- W4385574289 hasConcept C121332964 @default.
- W4385574289 hasConcept C154945302 @default.
- W4385574289 hasConcept C184337299 @default.
- W4385574289 hasConcept C192209626 @default.
- W4385574289 hasConcept C199360897 @default.
- W4385574289 hasConcept C204321447 @default.
- W4385574289 hasConcept C2777530160 @default.
- W4385574289 hasConcept C41008148 @default.
- W4385574289 hasConcept C51167844 @default.
- W4385574289 hasConcept C65965080 @default.
- W4385574289 hasConcept C89600930 @default.
- W4385574289 hasConceptScore W4385574289C111919701 @default.
- W4385574289 hasConceptScore W4385574289C118505674 @default.
- W4385574289 hasConceptScore W4385574289C119857082 @default.
- W4385574289 hasConceptScore W4385574289C120665830 @default.
- W4385574289 hasConceptScore W4385574289C121332964 @default.
- W4385574289 hasConceptScore W4385574289C154945302 @default.
- W4385574289 hasConceptScore W4385574289C184337299 @default.
- W4385574289 hasConceptScore W4385574289C192209626 @default.
- W4385574289 hasConceptScore W4385574289C199360897 @default.
- W4385574289 hasConceptScore W4385574289C204321447 @default.
- W4385574289 hasConceptScore W4385574289C2777530160 @default.
- W4385574289 hasConceptScore W4385574289C41008148 @default.
- W4385574289 hasConceptScore W4385574289C51167844 @default.
- W4385574289 hasConceptScore W4385574289C65965080 @default.
- W4385574289 hasConceptScore W4385574289C89600930 @default.
- W4385574289 hasLocation W43855742891 @default.
- W4385574289 hasOpenAccess W4385574289 @default.
- W4385574289 hasPrimaryLocation W43855742891 @default.
- W4385574289 hasRelatedWork W1492132281 @default.
- W4385574289 hasRelatedWork W159132833 @default.
- W4385574289 hasRelatedWork W1971791118 @default.
- W4385574289 hasRelatedWork W2124251782 @default.
- W4385574289 hasRelatedWork W2135875128 @default.
- W4385574289 hasRelatedWork W2787630118 @default.
- W4385574289 hasRelatedWork W2936858556 @default.
- W4385574289 hasRelatedWork W3089147533 @default.
- W4385574289 hasRelatedWork W3212418102 @default.
- W4385574289 hasRelatedWork W4378192631 @default.
- W4385574289 isParatext "false" @default.
- W4385574289 isRetracted "false" @default.
- W4385574289 workType "article" @default.