Mandarin word-character hybrid-input neural network language model
Moonyoung Kang, Tim Ng, Long Nguyen · 2011
We applied neural network language model (NNLM) on Chinese by training and testing it on 2011 GALE Mandarin evaluation task. Exploiting the fact that there are no word boundaries in written Chinese, we trained various NNLMs using either word, character, or both, including a wordcharacter hybrid-input NNLM which accepts both word and character as input. Our best result showed up to 0.6% absolute (6.3% relative) Character Error Rate (CER) reduction compared to an un-pruned 4-gram standard language model and 0.2% absolute (2.6% relative) CER reduction compared to a word-based NNLM. Index Terms: speech recognition, neural network language model