Preprocessing + Feature generation

FeatureGenFromRaw.java

package edu.washington.multir.experiment;

import java.io.IOException;
import java.util.List;

import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.util.CoreMap;
import edu.stanford.nlp.util.Pair;
import edu.washington.multir.preprocess.CorpusPreprocessing;
import edu.washington.multirframework.argumentidentification.ArgumentIdentification;
import edu.washington.multirframework.argumentidentification.DefaultSententialInstanceGeneration;
import edu.washington.multirframework.argumentidentification.NERArgumentIdentification;
import edu.washington.multirframework.argumentidentification.SententialInstanceGeneration;
import edu.washington.multirframework.data.Argument;
import edu.washington.multirframework.data.KBArgument;
import edu.washington.multirframework.featuregeneration.DefaultFeatureGenerator;
import edu.washington.multirframework.featuregeneration.FeatureGenerator;

public class FeatureGenFromRawText {
	public static void getFeatures(String sentence, String docName) {
		try {
			Annotation doc = CorpusPreprocessing.getTestDocumentFromRawString(sentence, docName);
			//Do argument identification and generate features
			//do argument identification
			ArgumentIdentification ai = NERArgumentIdentification.getInstance();
			SententialInstanceGeneration sig = DefaultSententialInstanceGeneration.getInstance();
			FeatureGenerator fg = new DefaultFeatureGenerator();
			
			List<CoreMap> docSentences = doc.get(CoreAnnotations.SentencesAnnotation.class);
			int count =0;
			for(CoreMap sent: docSentences){
				System.out.println("Sentence " + count);
				List<Argument> arguments = ai.identifyArguments(doc, sent);
				System.out.println("Arguments");
				for(Argument arg : arguments){
					System.out.println(arg.getArgName());
				}
				List<CoreLabel> tokens = sent.get(CoreAnnotations.TokensAnnotation.class);
				System.out.println("Token size = " + tokens.size());
				System.out.println("TOKENS");
				for(CoreLabel t: tokens){
					System.out.print(t + " ");
				}
				
				List<Pair<Argument,Argument>> sententialInstances = sig.generateSententialInstances(arguments, sent);
				for(Pair<Argument,Argument> argPair : sententialInstances){
					Argument arg1 = argPair.first;
					Argument arg2 = argPair.second;
					String arg1ID = null;
					String arg2ID = null;
					if(arg1 instanceof KBArgument){
						arg1ID = ((KBArgument)arg1).getKbId();
					}
					if(arg2 instanceof KBArgument){
						arg2ID = ((KBArgument)arg2).getKbId();
					}
					List<String> features =fg.generateFeatures(arg1.getStartOffset(),
											arg1.getEndOffset(),
											arg2.getStartOffset(),
											arg2.getEndOffset(), 
											arg1ID,arg2ID,
											sent, doc);
					System.out.print(arg1.getArgName() + "\t" + arg2.getArgName());
					for(String feature: features){
						System.out.print("\t" + feature);
					}
					System.out.println();
				}
				count++;
				
			}

		} catch (IOException | InterruptedException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	
	public static void main(String args[]) {
		FeatureGenFromRawText.getFeatures("Mongolia's trade with Russia has increased a lot", "doc");
	}
	
}

Output

Sentence 0
Arguments
Mongolia
Russia
Token size = 9
TOKENS
Mongolia 's trade with Russia has increased a lot here I am generating features!!!!!
Mongolia	Russia	inverse_false|LOCATION|'s trade with|LOCATION	inverse_false|B_-1|LOCATION|'s trade with|LOCATION|has	inverse_false|B_-2 B_-1|LOCATION|'s trade with|LOCATION|has increased	str:'s[possessive]->|LOCATION|[poss]->trade[nsubj]<-with[prep]<-|LOCATION	dep:[possessive]->|LOCATION|[poss]->[nsubj]<-[prep]<-|LOCATION	dir:->|LOCATION|-><-<-|LOCATION	str:LOCATION|[poss]->trade[nsubj]<-with[prep]<-|LOCATION
here I am generating features!!!!!
Russia	Mongolia	inverse_true|LOCATION|'s trade with|LOCATION	inverse_true|B_-1|LOCATION|'s trade with|LOCATION|has	inverse_true|B_-2 B_-1|LOCATION|'s trade with|LOCATION|has increased	str:LOCATION|[pobj]->with[prep]->trade[nsubj]<-|LOCATION|[possessive]->'s	dep:LOCATION|[pobj]->[prep]->[nsubj]<-|LOCATION|[possessive]->	dir:LOCATION|->-><-|LOCATION|->	str:LOCATION|[pobj]->with[prep]->trade[nsubj]<-|LOCATION