| W03-1724 | rules to correct mistakes in the | probabilistic segmentation | of ambiguous substrings . This |
| H92-1031 | He shows that incorporating a | probabilistic segmentation | model improves the performance |
| W95-0109 | training and cost . Practical | probabilistic segmentation | models can achieve quite satisfactory |
| P00-1078 | matching , maximal matching and | probabilistic segmentation | had been applied in the early |
| W03-1724 | If no rule is applicable , its | probabilistic segmentation | is retained . For the bakeoff |
| P08-1084 | frequent strings . Our work builds on | probabilistic segmentation | approaches such as Morfessor |
| W03-1724 | the language model is trained , | probabilistic segmentation | can not avoid mistakes on ambiguous |
| N03-1018 | may not be words . Therefore , a | probabilistic segmentation | model that accommodates word |
| W10-1760 | , ( Brent , 1999 ) proposes a | probabilistic segmentation | model based on unigram word distri |
| W03-1724 | detect the discrepancies of our | probabilistic segmentation | and the standard segmentation |
| W15-1108 | significant interest in the early | probabilistic segmentation | strategies infants use ( Brent |
| W03-1724 | general-purpose ngram model for | probabilistic segmentation | and a case - or example-based |
| W03-1724 | ( also denoted as cn1 ) , its | probabilistic segmentation | into a word sequence w1w2 · |
| N09-1040 | lexical chains . TEXTSEG employs a | probabilistic segmentation | objective that is similar to |
| W03-1724 | this side-effect : ( 1 ) retrain | probabilistic segmentation | -- a conservative strategy ; |
