Approaches to convert RNNLM to BNLM

main paper

comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[1]

related paper

• VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[2]
• Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[3]
• Converting Neural Network Language Models into　Back-off Language Models for Efficient Decoding　in Automatic Speech Recognition[4]

related algorithm

• gibbs sampling[5][6]
• Kullback–Leibler divergence[7]