public List<String> predictArgumentLines(Sentence sentence, List<String> idResult, int kBest)
throws IOException {
final List<FrameFeatures> frameFeaturesList = Lists.newArrayList();
final FeatureExtractor featureExtractor = new FeatureExtractor();
for (String feLine : idResult) {
final DataPointWithFrameElements dataPoint = new DataPointWithFrameElements(sentence, feLine);
final String frame = dataPoint.getFrameName();
final DependencyParses parses = dataPoint.getParses();
final int targetStartTokenIdx = dataPoint.getTargetTokenIdxs()[0];
final int targetEndTokenIdx =
dataPoint.getTargetTokenIdxs()[dataPoint.getTargetTokenIdxs().length - 1];
final List<SpanAndParseIdx> spans = DataPrep.findSpans(dataPoint, 1);
final List<String> frameElements =
Lists.newArrayList(frameElementsForFrame.lookupFrameElements(frame));
final List<SpanAndCorrespondingFeatures[]> featuresAndSpanByArgument = Lists.newArrayList();
for (String frameElement : frameElements) {
final List<SpanAndCorrespondingFeatures> spansAndFeatures = Lists.newArrayList();
for (SpanAndParseIdx candidateSpanAndParseIdx : spans) {
final Range0Based span = candidateSpanAndParseIdx.span;
final DependencyParse parse = parses.get(candidateSpanAndParseIdx.parseIdx);
final Set<String> featureSet =
featureExtractor
.extractFeatures(dataPoint, frame, frameElement, span, parse)
.elementSet();
final int[] featArray = convertToIdxs(featureSet);
spansAndFeatures.add(
new SpanAndCorrespondingFeatures(new int[] {span.start, span.end}, featArray));
}
featuresAndSpanByArgument.add(
spansAndFeatures.toArray(new SpanAndCorrespondingFeatures[spansAndFeatures.size()]));
}
frameFeaturesList.add(
new FrameFeatures(
frame,
targetStartTokenIdx,
targetEndTokenIdx,
frameElements,
featuresAndSpanByArgument));
}
return decoder.decodeAll(frameFeaturesList, idResult, 0, kBest);
}
public static Semafor getSemaforInstance(String modelDirectory)
throws IOException, ClassNotFoundException, URISyntaxException {
final String requiredDataFilename =
new File(modelDirectory, REQUIRED_DATA_FILENAME).getAbsolutePath();
final String alphabetFilename = new File(modelDirectory, ALPHABET_FILENAME).getAbsolutePath();
final String frameElementMapFilename =
new File(modelDirectory, FRAME_ELEMENT_MAP_FILENAME).getAbsolutePath();
final String argModelFilename = new File(modelDirectory, ARG_MODEL_FILENAME).getAbsolutePath();
// unpack required data
final RequiredDataForFrameIdentification r = readObject(requiredDataFilename);
final Set<String> allRelatedWords = r.getAllRelatedWords();
final GraphBasedFrameIdentifier idModel = GraphBasedFrameIdentifier.getInstance(modelDirectory);
final RoteSegmenter segmenter = new RoteSegmenter(allRelatedWords);
System.err.println("Initializing alphabet for argument identification..");
final Map<String, Integer> argIdFeatureIndex =
DataPrep.readFeatureIndex(new File(alphabetFilename));
final FEDict frameElementsForFrame = FEDict.fromFile(frameElementMapFilename);
final Decoding decoder = Decoding.fromFile(argModelFilename, alphabetFilename);
return new Semafor(
allRelatedWords, frameElementsForFrame, segmenter, idModel, decoder, argIdFeatureIndex);
}