| P01-1068 | connectivity characteristics . Better | word-clustering | is to be considered based on |
| W02-2028 | means , in terms of accuracy , | word-clustering | is not effective for SVMs . The |
| P98-2148 | pose , based on this report , a | word-clustering | method on the model we have mentioned |
| D14-1149 | of many existing approaches to | word-clustering | , is an underlying prioritization |
| P11-1001 | based model . Performance of the | word-clustering | based models To empirically validate |
| W14-6101 | tagset reduction , or through | word-clustering | . Lakeland ( 2005 ) uses lexicalized |
| P11-1001 | at seman - performance of the | word-clustering | based labeling tically similar |
| J11-1005 | perform semi-supervised learning by | word-clustering | and self-training , respectively |
| P05-1001 | captures the spirit of predictive | word-clustering | but is more general and effective |
| H05-1064 | objec - tive , whereas previous | word-clustering | approaches ( e.g. Brown et al. |
| H05-1064 | on unsupervised approaches to | word-clustering | or word-sense discovery is that |
| J00-1004 | have also tried using automatic | word-clustering | techniques to merge states further |
| J11-4008 | Kotropoulos ( 2011 ) investigate two | word-clustering | techniques that operate on long-distance |
| W97-0105 | his implementation of the Brown | word-clustering | algorithm ; and Craig MacDonald |
