DAgger-style imitation learning outperforms REINFORCE reinforcement learning for paraphrase generation with a pointer-generator, and the best model reaches state-of-the-art scores on Quora.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
DAgger-style imitation learning outperforms REINFORCE reinforcement learning for paraphrase generation with a pointer-generator, and the best model reaches state-of-the-art scores on Quora.