Factored recurrent neural network language model in TED lecture transcription.
Youzheng Wu, H. Yamamoto, Xugang Lu, Shigeki Matsuda, Chiori Hori, Hideki Kashioka · IWSLT · 2012
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.