DNPG is a multi-component Transformer model that disentangles paraphrase generation across granularity levels and supports unsupervised domain adaptation, claiming competitive in-domain and superior cross-domain performance.
Just remove or add some stop words
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decomposable Neural Paraphrase Generation
DNPG is a multi-component Transformer model that disentangles paraphrase generation across granularity levels and supports unsupervised domain adaptation, claiming competitive in-domain and superior cross-domain performance.