In this study, we extend recurrent neural network-based language models (RNNLMs) by explicitly integrating morphological and syntactic factors (or features). Our proposed RNNLM is called a factored RNNLM that is expected to enhance RNNLMs. A number of experiments are carried out on top of state-of-the-art LVCSR system that show the factored RNNLM improves the performance measured by perplexity and word error rate. In the IWSLT TED test data sets, absolute word error rate reductions over RNNLM and n-gram LM are 0.4~0.8 points.
Cite as: Wu, Y., Yamamoto, H., Lu, X., Matsuda, S., Hori, C., Kashioka, H. (2012) Factored recurrent neural network language model in TED lecture transcription. Proc. International Workshop on Spoken Language Translation (IWSLT 2012), 222-228
@inproceedings{wu12_iwslt,
author={Youzheng Wu and Hitoshi Yamamoto and Xugang Lu and Shigeki Matsuda and Chiori Hori and Hideki Kashioka},
title={{Factored recurrent neural network language model in TED lecture transcription}},
year=2012,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2012)},
pages={222--228}
}