Random forests and the data sparseness problem in language modeling

By Peng Xu, Frederick Jelinek. 2007

74 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

One billion word benchmark for measuring progress in statistical language modeling (2013, neutral): “• Random forest (Xu, 2005)”
Extensions of recurrent neural network language model (2011, methodology): “The combination of these networks is done by linear interpolation with equal weights assigned to each model (note similarity to random forests that are composed of different decision trees [8]).”
Statistical Language Models Based on Neural Networks (2012, methodology): “We used 4-gram features for the Random forest language model [78], that is a combination of several randomly grown decision trees.”
Prosodic and temporal features for language modeling for dialog (2012, unknown): “with n-gram information in better ways, perhaps by using probabilities instead of scaling factors (Section 3), or, more adventurously, by integrating non-lexical predictors into a more general framework (Bengio et al., 2003; Xu and Jelinek, 2007).”
Improving protein fold recognition by random forest (2014, background): “Random forest has been used extensively in a wide variety of domains [12-14] including protein fold classification [15-17], which is related to, but different than protein fold recognition.”
Structured Output Layer Neural Network Language Models for Speech Recognition (2013, background): “Moreover, if a word is assigned to a wrong class at some level in a decision tree, this error affects all the internal nodes (or clusters) leading to this word.”
Empirical Evaluation and Combination of Advanced Language Modeling Techniques (2011, methodology): “We used 4-gram features for the Random forest language model [6].”