We continue our investigations of Word-Phrase-Entity (WPE) Language Models that unify words, phrases and classes, such as named entities, into a single probabilistic framework for the purpose of language modeling. In the present study we show how WPE LMs can be adapted to work in a personalized scenario where class definitions change from user to user or even from utterance to utterance. Compared to traditional class-based LMs in various conditions, WPE LMs exhibited comparable or better modeling potential without requiring pre-tagged training material. We also significantly scaled the experimental setup by widening the target domain, amplifying the amount of training material and increasing the number of classes.
Cite as: Levit, M., Stolcke, A., Subba, R., Parthasarathy, S., Chang, S., Xie, S., Anastasakos, T., Dumoulin, B. (2015) Personalization of word-phrase-entity language models. Proc. Interspeech 2015, 448-452, doi: 10.21437/Interspeech.2015-173
@inproceedings{levit15_interspeech,
author={M. Levit and Andreas Stolcke and R. Subba and S. Parthasarathy and S. Chang and S. Xie and T. Anastasakos and Benoit Dumoulin},
title={{Personalization of word-phrase-entity language models}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={448--452},
doi={10.21437/Interspeech.2015-173}
}