private List<LabeledLocalTrigramContext> extractLabeledLocalTrigramContexts(
List<TaggedSentence> taggedSentences) {
List<LabeledLocalTrigramContext> localTrigramContexts =
new ArrayList<LabeledLocalTrigramContext>();
for (TaggedSentence taggedSentence : taggedSentences) {
localTrigramContexts.addAll(extractLabeledLocalTrigramContexts(taggedSentence));
}
return localTrigramContexts;
}
private static List<SentencePair> readSentencePairs(String path, int maxSentencePairs) {
List<SentencePair> sentencePairs = new ArrayList<SentencePair>();
List<String> baseFileNames = getBaseFileNames(path);
for (String baseFileName : baseFileNames) {
if (sentencePairs.size() >= maxSentencePairs)
continue;
sentencePairs.addAll(readSentencePairs(baseFileName));
}
return sentencePairs;
}
public static void main(String[] args) throws IOException {
// Parse command line flags and arguments
Map<String,String> argMap = CommandLineUtils.simpleCommandLineParser(args);
// Set up default parameters and settings
String basePath = ".";
int maxTrainingSentences = 0;
int maxIterations = 20;
boolean verbose = false;
boolean initialize = false;
String dataset = "mini";
String model = "baseline";
// Update defaults using command line specifications
if (argMap.containsKey("-path")) {
basePath = argMap.get("-path");
System.out.println("Using base path: "+basePath);
}
if (argMap.containsKey("-sentences")) {
maxTrainingSentences = Integer.parseInt(argMap.get("-sentences"));
System.out.println("Using an additional "+maxTrainingSentences+" training sentences.");
}
if (argMap.containsKey("-data")) {
dataset = argMap.get("-data");
System.out.println("Running with data: "+dataset);
} else {
System.out.println("No data set specified. Use -data [miniTest, validate].");
}
if (argMap.containsKey("-model")) {
model = argMap.get("-model");
System.out.println("Running with model: "+model);
} else {
System.out.println("No model specified. Use -model modelname.");
}
if (argMap.containsKey("-verbose")) {
verbose = true;
}
if (argMap.containsKey("-iterations")) {
maxIterations = Integer.parseInt(argMap.get("-iterations"));
}
if (argMap.containsKey("-initialize")) {
initialize = true;
}
// Read appropriate training and testing sets.
List<SentencePair> trainingSentencePairs = new ArrayList<SentencePair>();
if (! (dataset.equals("miniTest") || dataset.equals("mini")) && maxTrainingSentences > 0)
trainingSentencePairs = readSentencePairs(basePath+"/training", maxTrainingSentences);
List<SentencePair> testSentencePairs = new ArrayList<SentencePair>();
Map<Integer,Alignment> testAlignments = new HashMap<Integer, Alignment>();
if (dataset.equalsIgnoreCase("validate")) {
testSentencePairs = readSentencePairs(basePath+"/trial", Integer.MAX_VALUE);
testAlignments = readAlignments(basePath+"/trial/trial.wa");
} else if (dataset.equals("miniTest") || dataset.equals("mini")) {
testSentencePairs = readSentencePairs(basePath+"/mini", Integer.MAX_VALUE);
testAlignments = readAlignments(basePath+"/mini/mini.wa");
} else {
throw new RuntimeException("Bad data set mode: "+ dataset+", use validate or miniTest.");
}
trainingSentencePairs.addAll(testSentencePairs);
// Build model
WordAligner wordAligner = null;
if (model.equalsIgnoreCase("baseline")) {
wordAligner = new BaselineWordAligner();
}
// TODO : build other alignment models
else if (model.equalsIgnoreCase("heuristic")) {
wordAligner = new HeuristicWordAligner(trainingSentencePairs);
}
else if (model.equalsIgnoreCase("dice")) {
wordAligner = new DiceWordAligner(trainingSentencePairs);
}
else if (model.equalsIgnoreCase("ibm1") || model.equalsIgnoreCase("ibmModel1")) {
wordAligner = new IBMmodel1WordAligner(trainingSentencePairs, maxIterations, initialize);
}
else if (model.equalsIgnoreCase("ibm2") || model.equalsIgnoreCase("ibmModel2")) {
wordAligner = new IBMmodel2WordAligner(trainingSentencePairs, maxIterations, initialize);
}
// Test model
test(wordAligner, testSentencePairs, testAlignments, verbose);
// Generate file for submission //can comment out if not ready for submission
testSentencePairs = readSentencePairs(basePath+"/test", Integer.MAX_VALUE);
predict(wordAligner, testSentencePairs, basePath+"/"+model+".out");
}