Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200515392> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3200515392 abstract "Automatic paraphrase generation is an important task for natural language processing. However, progress in paraphrase generation has been hindered for a long time by the lack of large monolingual parallel corpora. We can alleviate the data shortage by effectively using multi-domain corpus. In this paper, we propose a novel model to exploit information from other source domains (out-of-domains) which benefits our target domain (in-domain). In our method, we maintain a private encoder and a private decoder for each domain which are used to model domain-specific information. In the meantime, we introduce a shared encoder and a shared decoder shared by all domains which only contain domain-independent information. Besides, we add a domain discriminator to the shared encoder to reinforce the ability to capture common features of shared encoder by adversarial training. Experimental results show that our method not only perform well in traditional domain adaptation tasks but also improve performance in all domains together. Moreover, we show that the shared layer learned by our proposed model can be regarded as an off-the-shelf layer and can be easily adapted to new domains." @default.
- W3200515392 created "2021-09-27" @default.
- W3200515392 creator A5018964554 @default.
- W3200515392 creator A5049887447 @default.
- W3200515392 creator A5071363838 @default.
- W3200515392 date "2021-01-01" @default.
- W3200515392 modified "2023-09-23" @default.
- W3200515392 title "Neural Paraphrase Generation with Multi-domain Corpus" @default.
- W3200515392 cites W2064675550 @default.
- W3200515392 cites W2101105183 @default.
- W3200515392 cites W2133512280 @default.
- W3200515392 cites W2740743644 @default.
- W3200515392 cites W2756978580 @default.
- W3200515392 cites W2760452458 @default.
- W3200515392 cites W2952481978 @default.
- W3200515392 cites W2962934171 @default.
- W3200515392 doi "https://doi.org/10.1007/978-3-030-86362-3_5" @default.
- W3200515392 hasPublicationYear "2021" @default.
- W3200515392 type Work @default.
- W3200515392 sameAs 3200515392 @default.
- W3200515392 citedByCount "0" @default.
- W3200515392 crossrefType "book-chapter" @default.
- W3200515392 hasAuthorship W3200515392A5018964554 @default.
- W3200515392 hasAuthorship W3200515392A5049887447 @default.
- W3200515392 hasAuthorship W3200515392A5071363838 @default.
- W3200515392 hasConcept C111919701 @default.
- W3200515392 hasConcept C118505674 @default.
- W3200515392 hasConcept C119857082 @default.
- W3200515392 hasConcept C134306372 @default.
- W3200515392 hasConcept C154945302 @default.
- W3200515392 hasConcept C165696696 @default.
- W3200515392 hasConcept C204321447 @default.
- W3200515392 hasConcept C2776214188 @default.
- W3200515392 hasConcept C2779803651 @default.
- W3200515392 hasConcept C2780922921 @default.
- W3200515392 hasConcept C33923547 @default.
- W3200515392 hasConcept C36503486 @default.
- W3200515392 hasConcept C37736160 @default.
- W3200515392 hasConcept C38652104 @default.
- W3200515392 hasConcept C41008148 @default.
- W3200515392 hasConcept C76155785 @default.
- W3200515392 hasConcept C94915269 @default.
- W3200515392 hasConceptScore W3200515392C111919701 @default.
- W3200515392 hasConceptScore W3200515392C118505674 @default.
- W3200515392 hasConceptScore W3200515392C119857082 @default.
- W3200515392 hasConceptScore W3200515392C134306372 @default.
- W3200515392 hasConceptScore W3200515392C154945302 @default.
- W3200515392 hasConceptScore W3200515392C165696696 @default.
- W3200515392 hasConceptScore W3200515392C204321447 @default.
- W3200515392 hasConceptScore W3200515392C2776214188 @default.
- W3200515392 hasConceptScore W3200515392C2779803651 @default.
- W3200515392 hasConceptScore W3200515392C2780922921 @default.
- W3200515392 hasConceptScore W3200515392C33923547 @default.
- W3200515392 hasConceptScore W3200515392C36503486 @default.
- W3200515392 hasConceptScore W3200515392C37736160 @default.
- W3200515392 hasConceptScore W3200515392C38652104 @default.
- W3200515392 hasConceptScore W3200515392C41008148 @default.
- W3200515392 hasConceptScore W3200515392C76155785 @default.
- W3200515392 hasConceptScore W3200515392C94915269 @default.
- W3200515392 hasLocation W32005153921 @default.
- W3200515392 hasOpenAccess W3200515392 @default.
- W3200515392 hasPrimaryLocation W32005153921 @default.
- W3200515392 hasRelatedWork W10075533 @default.
- W3200515392 hasRelatedWork W11816003 @default.
- W3200515392 hasRelatedWork W11991885 @default.
- W3200515392 hasRelatedWork W1670791 @default.
- W3200515392 hasRelatedWork W4649193 @default.
- W3200515392 hasRelatedWork W598832 @default.
- W3200515392 hasRelatedWork W7389446 @default.
- W3200515392 hasRelatedWork W8788258 @default.
- W3200515392 hasRelatedWork W9565258 @default.
- W3200515392 hasRelatedWork W10597021 @default.
- W3200515392 isParatext "false" @default.
- W3200515392 isRetracted "false" @default.
- W3200515392 magId "3200515392" @default.
- W3200515392 workType "book-chapter" @default.