| tech,3-5-P03-1051,bq | <term> words </term> . To improve the <term> | segmentation | </term> <term> accuracy </term> , we use an | #4709 To improve the segmentation accuracy, we use an unsupervised algorithm for automatically acquiring new stems from a 155 million word unsegmented corpus, and re-estimate the model parameters with the expanded vocabulary and training corpus. |
