dataset creation using feature extraction from text

Question

I am trying to extract a few features from text data of terrorist events to create a dataset. Using name entity recognition, I have successfully extracted the features like name, place, organization now I want to extract the number of members involved in the incidence.

The 2008 Mumbai attacks (also referred to as 26/11) were a series of terrorist attacks that took place in
November 2008, when 10 members of Lashkar-e-Taiba, a terrorist organization based in Pakistan,
carried out 12 coordinated shooting and bombing attacks lasting four days across Mumbai.

from the above text how can I extract 10 members of Lashkar-e-Taiba and place 10 in the column of the number of attackers. Is that even possible using nlp techniques?

Answer 1

The two techniques that could be useful in your case are - dependency parsing and semantic role labeling. You may also want to look up aspect based sentiment analysis. All three of these can help identify relationships between words in a sentence.