We need a .net 2.0 assembly (c# or [url removed, login to view] preferred) for segmenting chinese textstrings into words. Word segmentation should be done with a dictionary approach. Stop words and nouns should be marked as such but not removed. Output should be a string with words separated by spaces.
High Speed processing is also neccessity. Completion of processing must be in less than .5 sec per 300 chars on a p4. Dictionary may be held in memory to speed up processing if the dictionary is less than 100 mb in size.
Source files must be delivered