Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
Inside-Outside and Forward-Backward Algorithms Are Just Backprop (tutorial paper)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Diffusion training lets a CRF condition on noisy entire label sequences, yielding 16.5% error reduction on POS-tagging via approximate inference.
citing papers explorer
-
Syntactic Belief Update as the Driver of Garden Path Processing Difficulty
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
-
Approximate Structured Diffusion for Sequence Labelling
Diffusion training lets a CRF condition on noisy entire label sequences, yielding 16.5% error reduction on POS-tagging via approximate inference.