@inproceedings{levit2015token-level,
author = {Levit, Michael and Stolcke, Andreas and Chang, Shawn and Parthasarathy, Sarangarajan},
title = {Token-level Interpolation for Class-Based Language Models},
booktitle = {Proc. IEEE ICASSP},
year = {2015},
month = {April},
abstract = {We describe a method for interpolation of class-based n-gram language models. Our algorithm is an extension of the traditional EM-based approach that optimizes perplexity of the training set with respect to a collection of n-gram language models linearly combined in the probability space. However, unlike prior work, it naturally supports context-dependent interpolation for class-based LMs. In addition, the method works naturally with the recently introduced wordphrase-entity (WPE) language models that unify words, phrases and entities into a single statistical framework. Applied to the Calendar scenario of the Personal Assistant domain, our method achieved significant perplexity reduction and improved word error rates.},
publisher = {IEEE - Institute of Electrical and Electronics Engineers},
url = {http://approjects.co.za/?big=en-us/research/publication/token-level-interpolation-for-class-based-language-models/},
pages = {5426-5430},
edition = {Proc. IEEE ICASSP},
}