A latent sequence model with a globally normalized pairwise CRF observation model generates coherent text while keeping state transitions non-autoregressive.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Autoregressive Text Generation Beyond Feedback Loops
A latent sequence model with a globally normalized pairwise CRF observation model generates coherent text while keeping state transitions non-autoregressive.