Quantcast
Channel: Machine Learning
Viewing all articles
Browse latest Browse all 63295

Named Entity Recognition using stanford nlp core on parallel computing [Implementation Help]

$
0
0

Hi I need to implement the above, so far I have tried using Stanford NLP core and got it working on default settings. If i try to change the settings the server doesnt run, it error's out so I didnt really mess around with it its doing its job on default setup.

Language = Python

Lib = jsonrpclib, robert Elwell's python extension

I got the parser running to process the data on a single core, but i want to implement it on multiple cores. I tried Ipython for it, still learning about it and playing with it, though I have my doubts that its the best way to do this because I tried some sample testing it didn't work very efficiently but it could just be my implementation.

My prime target is processing 100 articles per second and the way I am doing it is not working, could you guys suggest ways to improve my performance.

Current performance = 7-15sec/article on local machine.

sorry for being a little gibberish. :) thank you.

submitted by heaven__
[link][2 comments]

Viewing all articles
Browse latest Browse all 63295

Trending Articles