Improved Training Of Neural Trans-Dimensional Random field Language Models with Dynamic Noise-Contrastive Estimation.

Bin Wang Zhijian Ou

Published in: SLT (2018)

Keyphrases

language model
random fields
probabilistic model
language modeling
parameter estimation
n gram
conditional random fields
context sensitive

document retrieval
speech recognition
information retrieval
retrieval model
query expansion
mixture model
language modelling
random field models

markov random field
test collection
maximum entropy
autoregressive
statistical language models
language models for information retrieval
non stationary
document ranking

smoothing methods
graphical models
generative model
pseudo relevance feedback
expectation maximization
maximum likelihood
training data