Integrating Pretrained Language Model for Dialogue Policy Evaluation.
Hongru WangHuimin WangZezhong WangKam-Fai WongPublished in: ICASSP (2022)
Keyphrases
- language model
- policy evaluation
- least squares
- language modeling
- n gram
- temporal difference
- probabilistic model
- reinforcement learning
- monte carlo
- model free
- retrieval model
- markov decision processes
- information retrieval
- query expansion
- mixture model
- variance reduction
- policy iteration
- ad hoc information retrieval
- function approximation
- translation model
- semi parametric
- natural language
- smoothing methods
- em algorithm
- classification accuracy
- support vector
- bayesian networks