public static void main(String[] args) {
if (args.length < minArgs) {
System.out.println(usage());
System.exit(-1);
}
Properties options = StringUtils.argsToProperties(args, argDefs());
Language language = PropertiesUtils.get(options, "l", Language.English, Language.class);
TreebankLangParserParams tlpp = language.params;
DiskTreebank tb = null;
String encoding = options.getProperty("l", "UTF-8");
boolean removeBracket = PropertiesUtils.getBool(options, "b", false);
tlpp.setInputEncoding(encoding);
tlpp.setOutputEncoding(encoding);
tb = tlpp.diskTreebank();
String[] files = options.getProperty("", "").split("\\s+");
if (files.length != 0) {
for (String filename : files) {
tb.loadPath(filename);
}
} else {
log.info(usage());
System.exit(-1);
}
PrintWriter pwo = tlpp.pw();
String startSymbol = tlpp.treebankLanguagePack().startSymbol();
TreeFactory tf = new LabeledScoredTreeFactory();
int nTrees = 0;
for (Tree t : tb) {
if (removeBracket) {
if (t.value().equals(startSymbol)) {
t = t.firstChild();
}
} else if (!t.value().equals(startSymbol)) { // Add a bracket if it isn't already there
t = tf.newTreeNode(startSymbol, Collections.singletonList(t));
}
pwo.println(t.toString());
nTrees++;
}
pwo.close();
System.err.printf("Processed %d trees.%n", nTrees);
}
/**
* Run the Evalb scoring metric on guess/gold input. The default language is English.
*
* @param args
*/
public static void main(String[] args) {
TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
int maxGoldYield = Integer.MAX_VALUE;
boolean VERBOSE = false;
String encoding = "UTF-8";
String guessFile = null;
String goldFile = null;
Map<String, String[]> argsMap = StringUtils.argsToMap(args, optionArgDefs);
for (Map.Entry<String, String[]> opt : argsMap.entrySet()) {
if (opt.getKey() == null) continue;
if (opt.getKey().equals("-l")) {
Language lang = Language.valueOf(opt.getValue()[0].trim());
tlpp = lang.params;
} else if (opt.getKey().equals("-y")) {
maxGoldYield = Integer.parseInt(opt.getValue()[0].trim());
} else if (opt.getKey().equals("-v")) {
VERBOSE = true;
} else if (opt.getKey().equals("-e")) {
encoding = opt.getValue()[0];
} else {
System.err.println(usage.toString());
System.exit(-1);
}
// Non-option arguments located at key null
String[] rest = argsMap.get(null);
if (rest == null || rest.length < minArgs) {
System.err.println(usage.toString());
System.exit(-1);
}
goldFile = rest[0];
guessFile = rest[1];
}
tlpp.setInputEncoding(encoding);
final PrintWriter pwOut = tlpp.pw();
final Treebank guessTreebank = tlpp.diskTreebank();
guessTreebank.loadPath(guessFile);
pwOut.println("GUESS TREEBANK:");
pwOut.println(guessTreebank.textualSummary());
final Treebank goldTreebank = tlpp.diskTreebank();
goldTreebank.loadPath(goldFile);
pwOut.println("GOLD TREEBANK:");
pwOut.println(goldTreebank.textualSummary());
final UnlabeledAttachmentEval metric =
new UnlabeledAttachmentEval("UAS LP/LR", true, tlpp.headFinder());
final TreeTransformer tc = tlpp.collinizer();
// The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
// In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
final Iterator<Tree> goldItr = goldTreebank.iterator();
final Iterator<Tree> guessItr = guessTreebank.iterator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.hasNext() && goldItr.hasNext()) {
Tree guessTree = guessItr.next();
List<? extends Label> guessYield = guessTree.yield();
guessLineId++;
Tree goldTree = goldItr.next();
List<? extends Label> goldYield = goldTree.yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.size() > maxGoldYield) {
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.size() != guessYield.size()) {
pwOut.printf(
"Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n",
goldYield.size(), guessYield.size(), goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
final Tree evalGuess = tc.transformTree(guessTree);
evalGuess.indexLeaves(true);
final Tree evalGold = tc.transformTree(goldTree);
evalGold.indexLeaves(true);
metric.evaluate(evalGuess, evalGold, ((VERBOSE) ? pwOut : null));
}
if (guessItr.hasNext() || goldItr.hasNext()) {
System.err.printf(
"Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.",
guessLineId, goldLineId);
}
pwOut.println(
"================================================================================");
if (skippedGuessTrees != 0)
pwOut.printf("%s %d guess trees\n", "Unable to evaluate", skippedGuessTrees);
metric.display(true, pwOut);
pwOut.println();
pwOut.close();
}
/** Execute with no arguments for usage. */
public static void main(String[] args) {
if (!validateCommandLine(args)) {
System.err.println(USAGE);
System.exit(-1);
}
final TreebankLangParserParams tlpp = LANGUAGE.params;
final PrintWriter pwOut = tlpp.pw();
final Treebank guessTreebank = tlpp.diskTreebank();
guessTreebank.loadPath(guessFile);
pwOut.println("GUESS TREEBANK:");
pwOut.println(guessTreebank.textualSummary());
final Treebank goldTreebank = tlpp.diskTreebank();
goldTreebank.loadPath(goldFile);
pwOut.println("GOLD TREEBANK:");
pwOut.println(goldTreebank.textualSummary());
final LeafAncestorEval metric = new LeafAncestorEval("LeafAncestor");
final TreeTransformer tc = tlpp.collinizer();
// The evalb ref implementation assigns status for each tree pair as follows:
//
// 0 - Ok (yields match)
// 1 - length mismatch
// 2 - null parse e.g. (()).
//
// In the cases of 1,2, evalb does not include the tree pair in the LP/LR computation.
final Iterator<Tree> goldItr = goldTreebank.iterator();
final Iterator<Tree> guessItr = guessTreebank.iterator();
int goldLineId = 0;
int guessLineId = 0;
int skippedGuessTrees = 0;
while (guessItr.hasNext() && goldItr.hasNext()) {
Tree guessTree = guessItr.next();
List<? extends Label> guessYield = guessTree.yield();
guessLineId++;
Tree goldTree = goldItr.next();
List<? extends Label> goldYield = goldTree.yield();
goldLineId++;
// Check that we should evaluate this tree
if (goldYield.size() > MAX_GOLD_YIELD) {
skippedGuessTrees++;
continue;
}
// Only trees with equal yields can be evaluated
if (goldYield.size() != guessYield.size()) {
pwOut.printf(
"Yield mismatch gold: %d tokens vs. guess: %d tokens (lines: gold %d guess %d)%n",
goldYield.size(), guessYield.size(), goldLineId, guessLineId);
skippedGuessTrees++;
continue;
}
final Tree evalGuess = tc.transformTree(guessTree);
final Tree evalGold = tc.transformTree(goldTree);
metric.evaluate(evalGuess, evalGold, ((VERBOSE) ? pwOut : null));
}
if (guessItr.hasNext() || goldItr.hasNext()) {
System.err.printf(
"Guess/gold files do not have equal lengths (guess: %d gold: %d)%n.",
guessLineId, goldLineId);
}
pwOut.println(
"================================================================================");
if (skippedGuessTrees != 0)
pwOut.printf("%s %d guess trees%n", "Unable to evaluate", skippedGuessTrees);
metric.display(true, pwOut);
pwOut.close();
}