Stochastic Estimation of Transduced Language Models
Transduced language models (TLMs) compose a pretrained \emph{source} language model with a functional finite-state transducer to induce a language model over \emph{target} strings. Computing the probability of a target prefix under a TLM amounts to summing the source-model probabilities of all source strings that the transducer maps to target strings beginning with that prefix. This set can be exponentially large or infinite. Prior work uses a computational shortcut based on source prefix probabilities, then approximates the resulting sum with threshold-pruned beam summing. This produces a low
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Vésteinn Snæbjarnarson →
“Stochastic Estimation of Transduced Language Models”
- LinkedLinked via arxiv author · 85%Samuel Kiegeland →
“Stochastic Estimation of Transduced Language Models”
- LinkedLinked via arxiv author · 85%Manuel de Prada Corral →
“Stochastic Estimation of Transduced Language Models”
- LinkedLinked via arxiv author · 85%Ryan Cotterell →
“Stochastic Estimation of Transduced Language Models”
- LinkedLinked via arxiv author · 85%Tim Vieira →
“Stochastic Estimation of Transduced Language Models”
- PossiblePossibly related (embedding) · 53%Large language models as uncertainty-calibrated optimizers for experimental discovery →