search

datumbox / datumbox-framework

Datumbox is an open-source Machine Learning framework written in Java which allows the rapid development of Machine Learning and Statistical applications.
http://www.datumbox.com/
Apache License 2.0
1.09k stars 283 forks source link

Can we perform Named Entity Extraction Using Datumbox #17

Open dilipbobby opened 7 years ago

dilipbobby commented 7 years ago

I want to know does datumbox help us in Named Entity Extraction or Named Entity recognition?__

datumbox commented 7 years ago

Unfortunately at the moment Datumbox does not provide an out of the box Named Entity Extraction algorithm. You can build one using the algorithms provided in the framework but this is not a trivial task. If you do, please consider contributing the code by sending a pull-request.

Here are some references on how you could formulate it as a classification problem and use the Multinomial Naive Bayes algorithm: https://arxiv.org/pdf/1509.04385.pdf https://web.stanford.edu/class/cs124/lec/Information_Extraction_and_Named_Entity_Recognition.pdf

dilipbobby commented 7 years ago

yes.I will try it from my side :) thanks