A unified neural model with a bi-LSTM sentence encoder, bilinear relation layer, lightweight-convolution global module, and an adaptive window-level ranking loss achieves state-of-the-art coherence discrimination on WSJ and on a new local-order benchmark.
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
-
A Unified Neural Coherence Model
A unified neural model with a bi-LSTM sentence encoder, bilinear relation layer, lightweight-convolution global module, and an adaptive window-level ranking loss achieves state-of-the-art coherence discrimination on WSJ and on a new local-order benchmark.