Hi, On 2007/08/07, at 20:55, Nicholas Volk wrote:
Dear all, I have some problems about model training,1. If the training corpus is larger (for example,10,000 sentences), the training process will crash because of memory consuming(about 2GB). Couldit be solved?If you are using Cygwin and pre-Vista OS, this is a Windows-related issue.Said OSs can not allocate more than 2GM for any single process. (Some Professional versions excluded.) br, Nicholas
If you are using relatively old linux/unix, there are another problem linked to this situation. Please see http://en.wikipedia.org/wiki/Large_file_supportJunichi