Abstract: We present an application of randomization techniques to class-based n-gram language models used in speech recognizers.

The idea is to de- rive a language model from the combination of a set of random class-based models. Each of the constituent random class-based models is built ...

This paper introduces a modification of the exchange clustering algorithm with improved eciency for certain partially class-based models and a distributed ...

The random cluster model is a random graph that generalizes and unifies the Ising model, Potts model, and percolation model.

First, each word is initialized to a random cluster. Then, at each iteration, every word is moved to a cluster such that the resulting model has the minimum ...

Dec 31, 2023 · In this paper, we propose ClusterClip Sampling to balance the text distribution of training data for better model training.

Aug 11, 2024 · Specifically, ClusterClip Sampling utilizes data clustering to reflect the data distribution of the training set and balances the common samples.

Dec 2, 2024 · Text clustering serves as a preliminary step in various text analysis tasks, including topic modelling, trend analysis, and sentiment analysis.

May 23, 2024 · The random language model [Phys. Rev. Lett. 122, 128301 (2019)] is an ensemble of stochastic context-free grammars, quantifying the syntax of human and ...

Once constructed, the RFs function as a randomized his- tory clustering which can help in dealing with the data sparseness problem. Although they do not per-.