public static void main(String[] args) throws Exception {
// Parse command line flags and arguments
Map<String, String> argMap = CommandLineUtils.simpleCommandLineParser(args);
// Set up default parameters and settings
String basePath = ".";
boolean verbose = false;
// Update defaults using command line specifications
// The path to the assignment data
if (argMap.containsKey("-path")) {
basePath = argMap.get("-path");
}
System.out.println("Using base path: " + basePath);
// Whether or not to print the individual errors.
if (argMap.containsKey("-verbose")) {
verbose = true;
}
// Read in data
System.out.print("Loading training sentences...");
List<TaggedSentence> trainTaggedSentences =
readTaggedSentences(basePath + "/en-wsj-train.pos", true);
Set<String> trainingVocabulary = extractVocabulary(trainTaggedSentences);
System.out.println("done.");
System.out.print("Loading in-domain dev sentences...");
List<TaggedSentence> devInTaggedSentences =
readTaggedSentences(basePath + "/en-wsj-dev.pos", true);
System.out.println("done.");
System.out.print("Loading out-of-domain dev sentences...");
List<TaggedSentence> devOutTaggedSentences =
readTaggedSentences(basePath + "/en-web-weblogs-dev.pos", true);
System.out.println("done.");
System.out.print("Loading out-of-domain blind test sentences...");
List<TaggedSentence> testSentences =
readTaggedSentences(basePath + "/en-web-test.blind", false);
System.out.println("done.");
// Construct tagger components
// TODO : improve on the MostFrequentTagScorer
LocalTrigramScorer localTrigramScorer = new MostFrequentTagScorer(false);
// TODO : improve on the GreedyDecoder
TrellisDecoder<State> trellisDecoder = new GreedyDecoder<State>();
// Train tagger
POSTagger posTagger = new POSTagger(localTrigramScorer, trellisDecoder);
posTagger.train(trainTaggedSentences);
// Optionally tune hyperparameters on dev data
posTagger.validate(devInTaggedSentences);
// Test tagger
System.out.println("Evaluating on in-domain data:.");
evaluateTagger(posTagger, devInTaggedSentences, trainingVocabulary, verbose);
System.out.println("Evaluating on out-of-domain data:.");
evaluateTagger(posTagger, devOutTaggedSentences, trainingVocabulary, verbose);
labelTestSet(posTagger, testSentences, basePath + "/en-web-test.tagged");
}
/**
* @param unusedLocale the wanted locale (actually unused).
* @throws MavenReportException if any
*/
protected void executeReport(Locale unusedLocale) throws MavenReportException {
File config = buildConfigurationFile();
Commandline cli = new Commandline();
cli.setWorkingDirectory(getBasedir().getAbsolutePath());
cli.setExecutable(getExecutablePath());
cli.createArgument().setValue(config.getAbsolutePath());
Writer stringWriter = new StringWriter();
StreamConsumer out = new WriterStreamConsumer(stringWriter);
StreamConsumer err = new WriterStreamConsumer(stringWriter);
try {
int returnCode = CommandLineUtils.executeCommandLine(cli, out, err);
if (!isQuiet()) {
// Get all output from doxygen and put it to the log out of Maven.
String[] lines = stringWriter.toString().split("\n");
for (int i = 0; i < lines.length; i++) {
lines[i] = lines[i].replaceAll("\n|\r", "");
getLog().info("doxygen: " + lines[i]);
}
}
if (returnCode != 0) {
throw new MavenReportException("Failed to generate Doxygen documentation.");
}
} catch (CommandLineException ex) {
throw new MavenReportException("Error while executing Doxygen.", ex);
}
}
public static void main(String[] args) {
// set up default options ..............................................
Map<String, String> options = new HashMap<String, String>();
options.put("--path", "../data/parser/");
options.put("--data", "masc");
options.put("--parser", "nlpclass.assignments.PCFGParserTester$BaselineParser");
options.put("--maxLength", "20");
// let command-line options supersede defaults .........................
options.putAll(CommandLineUtils.simpleCommandLineParser(args));
System.out.println("PCFGParserTester options:");
for (Map.Entry<String, String> entry : options.entrySet()) {
System.out.printf(" %-12s: %s%n", entry.getKey(), entry.getValue());
}
System.out.println();
MAX_LENGTH = Integer.parseInt(options.get("--maxLength"));
Parser parser;
try {
Class parserClass = Class.forName(options.get("--parser"));
parser = (Parser) parserClass.newInstance();
} catch (Exception e) {
throw new RuntimeException(e);
}
System.out.println("Using parser: " + parser);
String basePath = options.get("--path");
String preBasePath = basePath;
String dataSet = options.get("--data");
if (!basePath.endsWith("/")) {
basePath += "/";
}
// basePath += dataSet;
System.out.println("Data will be loaded from: " + basePath + "\n");
List<Tree<String>> trainTrees = new ArrayList<Tree<String>>();
List<Tree<String>> validationTrees = new ArrayList<Tree<String>>();
List<Tree<String>> testTrees = new ArrayList<Tree<String>>();
if (dataSet.equals("miniTest")) {
// training data: first 3 of 4 datums
basePath += "parser/" + dataSet;
System.out.println("Loading training trees...");
trainTrees = readTrees(basePath, 1, 3);
System.out.println("done.");
// test data: last of 4 datums
System.out.println("Loading test trees...");
testTrees = readTrees(basePath, 4, 4);
System.out.println("done.");
} else if (dataSet.equals("masc")) {
basePath += "parser/";
// training data: MASC train
System.out.println("Loading MASC training trees... from: " + basePath + "masc/train");
trainTrees.addAll(readMASCTrees(basePath + "masc/train", 0, 38));
System.out.println("done.");
System.out.println("Train trees size: " + trainTrees.size());
System.out.println("First train tree: " + Trees.PennTreeRenderer.render(trainTrees.get(0)));
System.out.println(
"Last train tree: "
+ Trees.PennTreeRenderer.render(trainTrees.get(trainTrees.size() - 1)));
// test data: MASC devtest
System.out.println("Loading MASC test trees...");
testTrees.addAll(readMASCTrees(basePath + "masc/devtest", 0, 11));
// testTrees.addAll(readMASCTrees(basePath+"masc/blindtest", 0, 8));
System.out.println("Test trees size: " + testTrees.size());
System.out.println("done.");
System.out.println("First test tree: " + Trees.PennTreeRenderer.render(testTrees.get(0)));
System.out.println(
"Last test tree: " + Trees.PennTreeRenderer.render(testTrees.get(testTrees.size() - 1)));
} else if (!dataSet.equals("miniTest") && !dataSet.equals("masc")) {
throw new RuntimeException("Bad data set: " + dataSet + ": use miniTest or masc.");
}
System.out.println("\nTraining parser...");
parser.train(trainTrees);
System.out.println("\nTesting parser...");
testParser(parser, testTrees);
}
public static void main(String[] args) {
// set up default options ..............................................
Map<String, String> options = new HashMap<String, String>();
options.put("-path", "/afs/ir/class/cs224n/pa2/data/");
options.put("-data", "miniTest");
options.put("-parser", "cs224n.assignments.PCFGParserTester$BaselineParser");
options.put("-maxLength", "20");
// let command-line options supersede defaults .........................
options.putAll(CommandLineUtils.simpleCommandLineParser(args));
System.out.println("PCFGParserTester options:");
for (Map.Entry<String, String> entry : options.entrySet()) {
System.out.printf(" %-12s: %s%n", entry.getKey(), entry.getValue());
}
System.out.println();
MAX_LENGTH = Integer.parseInt(options.get("-maxLength"));
Parser parser;
try {
Class parserClass = Class.forName(options.get("-parser"));
parser = (Parser) parserClass.newInstance();
} catch (Exception e) {
throw new RuntimeException(e);
}
System.out.println("Using parser: " + parser);
String basePath = options.get("-path");
String dataSet = options.get("-data");
if (!basePath.endsWith("/")) basePath += "/";
// basePath += dataSet;
System.out.println("Data will be loaded from: " + basePath + "\n");
List<Tree<String>> trainTrees = new ArrayList<Tree<String>>(),
validationTrees = new ArrayList<Tree<String>>(),
testTrees = new ArrayList<Tree<String>>();
if (!basePath.endsWith("/")) basePath += "/";
basePath += dataSet;
if (dataSet.equals("miniTest")) {
System.out.print("Loading training trees...");
trainTrees = readTrees(basePath, 1, 3);
System.out.println("done.");
System.out.print("Loading test trees...");
testTrees = readTrees(basePath, 4, 4);
System.out.println("done.");
} else if (dataSet.equals("treebank")) {
System.out.print("Loading training trees...");
trainTrees = readTrees(basePath, 200, 2199);
System.out.println("done.");
System.out.print("Loading validation trees...");
validationTrees = readTrees(basePath, 2200, 2202);
System.out.println("done.");
System.out.print("Loading test trees...");
testTrees = readTrees(basePath, 2300, 2319); // 2301);
System.out.println("done.");
} else {
throw new RuntimeException("Bad data set mode: " + dataSet + ", use miniTest, or treebank.");
}
parser.train(trainTrees);
testParser(parser, testTrees);
}
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");
}