Hi all, I noticed on the dev mailing list the mention of CRF models trained with mallet. I'm interested in perhaps comparing the performance of the ME model on the sourceforge page with a self-trained model using CRF. Apparently the capability to do this is in the sandbox.
https://mail-archives.apache.org/mod_mbox/opennlp-dev/201511.mbox/%3C144727 8070.4665.69.ca...@gmail.com%3E I'm a complete newbie to Java and the Apache development model in general. So, what exactly is the sandbox? Are there considerations to watch out for when using code here? (I'm guessing that it's stuff considered not-quite-ready for primetime yet.) Is there any code floating around that shows an example of the pluggable integration in action? The main goal here is to learn some more about the innards of OpenNLP, Java, and NLP model training generally, rather than doing anything in a production environment (yet). Thanks, Chris -- Christopher H. Greer | KPMG Data and Analytics | Denver | +1 773 680 6951 ********************************************************************** The information in this email is confidential and may be legally privileged. It is intended solely for the addressee. Access to this email by anyone else is unauthorized. If you are not the intended recipient, any disclosure, copying, distribution or any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. When addressed to our clients any opinions or advice contained in this email are subject to the terms and conditions expressed in the governing KPMG client engagement letter. ***********************************************************************
