public Extraction extract (Tokenization spans) { // We assume the input is unpiped. Instance carrier = featurePipe.pipe (new Instance (spans, null, null, null)); Sequence output = crf.transduce ((Sequence) carrier.getData ()); Extraction extraction = new Extraction (this, getTargetAlphabet()); DocumentExtraction docseq = new DocumentExtraction ("Extraction", getTargetAlphabet(), spans, output, null, backgroundTag, filter); extraction.addDocumentExtraction (docseq); return extraction; }
public Extraction extract (Tokenization spans) { // We assume the input is unpiped. Instance carrier = featurePipe.pipe (new Instance (spans, null, null, null)); Sequence output = crf.transduce ((Sequence) carrier.getData ()); Extraction extraction = new Extraction (this, getTargetAlphabet()); DocumentExtraction docseq = new DocumentExtraction ("Extraction", getTargetAlphabet(), spans, output, null, backgroundTag, filter); extraction.addDocumentExtraction (docseq); return extraction; }
public Extraction extract (Tokenization spans) { // We assume the input is unpiped. Instance carrier = featurePipe.pipe (new Instance (spans, null, null, null)); Sequence output = crf.transduce ((Sequence) carrier.getData ()); Extraction extraction = new Extraction (this, getTargetAlphabet()); DocumentExtraction docseq = new DocumentExtraction ("Extraction", getTargetAlphabet(), spans, output, null, backgroundTag, filter); extraction.addDocumentExtraction (docseq); return extraction; }
/** Assumes Instance.source contains the Tokenization object. */ public Extraction extract (InstanceList ilist) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); for (int i = 0; i < ilist.size(); i++) { Instance inst = ilist.get(i); Tokenization tok = (Tokenization)inst.getSource(); String name = inst.getName().toString(); Sequence input = (Sequence)inst.getData (); Sequence target = (Sequence)inst.getTarget (); Sequence output = crf.transduce(input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet(), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }
/** Assumes Instance.source contains the Tokenization object. */ public Extraction extract (InstanceList ilist) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); for (int i = 0; i < ilist.size(); i++) { Instance inst = ilist.get(i); Tokenization tok = (Tokenization)inst.getSource(); String name = inst.getName().toString(); Sequence input = (Sequence)inst.getData (); Sequence target = (Sequence)inst.getTarget (); Sequence output = crf.transduce(input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet(), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }
/** Assumes Instance.source contains the Tokenization object. */ public Extraction extract (InstanceList ilist) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); for (int i = 0; i < ilist.size(); i++) { Instance inst = ilist.get(i); Tokenization tok = (Tokenization)inst.getSource(); String name = inst.getName().toString(); Sequence input = (Sequence)inst.getData (); Sequence target = (Sequence)inst.getTarget (); Sequence output = crf.transduce(input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet(), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }
public Extraction extract (Iterator<Instance> source) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); // Put all the instances through both pipes, then get viterbi path InstanceList tokedList = new InstanceList (tokenizationPipe); tokedList.addThruPipe (source); InstanceList pipedList = new InstanceList (getFeaturePipe ()); pipedList.addThruPipe (tokedList.iterator()); Iterator<Instance> it1 = tokedList.iterator (); Iterator<Instance> it2 = pipedList.iterator (); while (it1.hasNext()) { Instance toked = it1.next(); Instance piped = it2.next (); Tokenization tok = (Tokenization) toked.getData(); String name = piped.getName().toString(); Sequence input = (Sequence) piped.getData (); Sequence target = (Sequence) piped.getTarget (); Sequence output = crf.transduce (input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet (), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }
public Extraction extract (Iterator<Instance> source) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); // Put all the instances through both pipes, then get viterbi path InstanceList tokedList = new InstanceList (tokenizationPipe); tokedList.addThruPipe (source); InstanceList pipedList = new InstanceList (getFeaturePipe ()); pipedList.addThruPipe (tokedList.iterator()); Iterator<Instance> it1 = tokedList.iterator (); Iterator<Instance> it2 = pipedList.iterator (); while (it1.hasNext()) { Instance toked = it1.next(); Instance piped = it2.next (); Tokenization tok = (Tokenization) toked.getData(); String name = piped.getName().toString(); Sequence input = (Sequence) piped.getData (); Sequence target = (Sequence) piped.getTarget (); Sequence output = crf.transduce (input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet (), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }
public Extraction extract (Iterator<Instance> source) { Extraction extraction = new Extraction (this, getTargetAlphabet ()); // Put all the instances through both pipes, then get viterbi path InstanceList tokedList = new InstanceList (tokenizationPipe); tokedList.addThruPipe (source); InstanceList pipedList = new InstanceList (getFeaturePipe ()); pipedList.addThruPipe (tokedList.iterator()); Iterator<Instance> it1 = tokedList.iterator (); Iterator<Instance> it2 = pipedList.iterator (); while (it1.hasNext()) { Instance toked = it1.next(); Instance piped = it2.next (); Tokenization tok = (Tokenization) toked.getData(); String name = piped.getName().toString(); Sequence input = (Sequence) piped.getData (); Sequence target = (Sequence) piped.getTarget (); Sequence output = crf.transduce (input); DocumentExtraction docseq = new DocumentExtraction (name, getTargetAlphabet (), tok, output, target, backgroundTag, filter); extraction.addDocumentExtraction (docseq); } return extraction; }