| P06-1126 | pruning . Section 3 proposes our | discriminative pruning method | for Chinese word segmentation |
| P06-1126 | . In this paper , we propose a | discriminative pruning method | of n-gram language model for |
| P06-1126 | Experimental results showed that the | discriminative pruning method | achieves significant improvements |
| P06-1126 | Experimental results show that the | discriminative pruning method | leads to a much smaller model |
| P06-1126 | Abstract This paper presents a | discriminative pruning method | of n-gram language model for |
| P06-1126 | Figure 2 and Figure 4 are used for | discriminative pruning method | . Growing algorithms are not |
| P06-1126 | In addition , by combining the | discriminative pruning method | with the baseline method , we |
| P06-1126 | currently the unigram model . For the | discriminative pruning method | suggested in this paper , growing |
