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