Dear Archana,

Topic modelling with MALLET (http://mallet.cs.umass.edu/) could be a solution for your needs.

Kind regards,

Olivier PARISOT

Hi Archana,

There are many tools for doing NLP research. You may try these:

1. Apache OpenNLP (https://opennlp.apache.org/)

2. Stanford NLP (http://nlp.stanford.edu/software/)

3. Clear NLP (https://code.google.com/p/clearnlp/)

4. Tree Tagger (http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/)

Dear Archana,

You might use some terminology extractor, for example, TTC TermSuite ( http://code.google.com/p/ttc-project/).

Hope it will help,

Yuliya

http://code.google.com/p/ttc-project/

If you are looking for a ready-made solution (for a very large number of languages), you can try with Sketch Engine (go to Wordlist -> Keywords). [Disclaimer: I'm one of the developers]

http://www.sketchengine.co.uk

I find writing my own code in Perl (particular with its regex support) is a good alternative. You get exactly what you want.

see also this related question: https://www.researchgate.net/post/Does_anyone_know_a_good_on-line_terminology_extraction_software_for_FR_and_DE_Does_anyone_know_a_good_BILINGUAL_multi-word_term_extractor

Thank you all!

You can write your own code in matlab as well to get the terms out of the document 

If  you know how to programm in Java then you could use Mallet : http://mallet.cs.umass.edu

Or this tool here : http://nlp.stanford.edu/software/

i guess it late reply, this may help others wrote java library to extract the stopping and stemmer words from given link/file/text i guess that may help you.

demo link: https://exude.herokuapp.com/

source code of library git : https://github.com/uttesh/exude

OpenNLP simple and practice lib to text processing.

how can we customize named entity recognition in open NLP

Most of the links shared in this thread are not working anymore. Some do work when copy pasted instead of directly clicking on them.