/**
* Provides some testing and opportunities for exploration of the probabilities of a BaseLexicon.
* What's here currently probably only works for the English Penn Treeebank, as it uses default
* constructors. Of the words given to test on, the first is treated as sentence initial, and the
* rest as not sentence initial.
*
* @param args The command line arguments: java BaseLexicon treebankPath fileRange
* unknownWordModel words*
*/
public static void main(String[] args) {
if (args.length < 3) {
System.err.println("java BaseLexicon treebankPath fileRange unknownWordModel words*");
return;
}
System.out.print("Training BaseLexicon from " + args[0] + ' ' + args[1] + " ... ");
Treebank tb = new DiskTreebank();
tb.loadPath(args[0], new NumberRangesFileFilter(args[1], true));
// TODO: change this interface so the lexicon creates its own indices?
Index<String> wordIndex = new HashIndex<String>();
Index<String> tagIndex = new HashIndex<String>();
BaseLexicon lex = new BaseLexicon(wordIndex, tagIndex);
lex.getUnknownWordModel().setUnknownLevel(Integer.parseInt(args[2]));
lex.train(tb);
System.out.println("done.");
System.out.println();
NumberFormat nf = NumberFormat.getNumberInstance();
nf.setMaximumFractionDigits(4);
List<String> impos = new ArrayList<String>();
for (int i = 3; i < args.length; i++) {
if (lex.isKnown(args[i])) {
System.out.println(
args[i] + " is a known word. Log probabilities [log P(w|t)] for its taggings are:");
for (Iterator<IntTaggedWord> it =
lex.ruleIteratorByWord(wordIndex.indexOf(args[i], true), i - 3, null);
it.hasNext(); ) {
IntTaggedWord iTW = it.next();
System.out.println(
StringUtils.pad(iTW, 24) + nf.format(lex.score(iTW, i - 3, wordIndex.get(iTW.word))));
}
} else {
String sig = lex.getUnknownWordModel().getSignature(args[i], i - 3);
System.out.println(
args[i]
+ " is an unknown word. Signature with uwm "
+ lex.getUnknownWordModel().getUnknownLevel()
+ ((i == 3) ? " init" : "non-init")
+ " is: "
+ sig);
impos.clear();
List<String> lis = new ArrayList<String>(tagIndex.objectsList());
Collections.sort(lis);
for (String tStr : lis) {
IntTaggedWord iTW = new IntTaggedWord(args[i], tStr, wordIndex, tagIndex);
double score = lex.score(iTW, 1, args[i]);
if (score == Float.NEGATIVE_INFINITY) {
impos.add(tStr);
} else {
System.out.println(StringUtils.pad(iTW, 24) + nf.format(score));
}
}
if (impos.size() > 0) {
System.out.println(args[i] + " impossible tags: " + impos);
}
}
System.out.println();
}
}
/** For testing: loads a treebank and prints the trees. */
public static void main(String[] args) {
TreebankLangParserParams tlpp = new ChineseTreebankParserParams();
System.out.println("Default encoding is: " + tlpp.diskTreebank().encoding());
if (args.length < 2) {
printlnErr(
"Usage: edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams treesPath fileRange");
} else {
Treebank m = tlpp.diskTreebank();
m.loadPath(args[0], new NumberRangesFileFilter(args[1], false));
for (Tree t : m) {
t.pennPrint(tlpp.pw());
}
System.out.println("There were " + m.size() + " trees.");
}
}
private Distribution<Integer> getSegmentedWordLengthDistribution(Treebank tb) {
// CharacterLevelTagExtender ext = new CharacterLevelTagExtender();
ClassicCounter<Integer> c = new ClassicCounter<Integer>();
for (Iterator iterator = tb.iterator(); iterator.hasNext(); ) {
Tree gold = (Tree) iterator.next();
StringBuilder goldChars = new StringBuilder();
ArrayList goldYield = gold.yield();
for (Iterator wordIter = goldYield.iterator(); wordIter.hasNext(); ) {
Word word = (Word) wordIter.next();
goldChars.append(word);
}
List<HasWord> ourWords = segment(goldChars.toString());
for (int i = 0; i < ourWords.size(); i++) {
c.incrementCount(Integer.valueOf(ourWords.get(i).word().length()));
}
}
return Distribution.getDistribution(c);
}
public static void main(String[] args) {
Options op = new Options(new EnglishTreebankParserParams());
// op.tlpParams may be changed to something else later, so don't use it till
// after options are parsed.
System.out.println(StringUtils.toInvocationString("FactoredParser", args));
String path = "/u/nlp/stuff/corpora/Treebank3/parsed/mrg/wsj";
int trainLow = 200, trainHigh = 2199, testLow = 2200, testHigh = 2219;
String serializeFile = null;
int i = 0;
while (i < args.length && args[i].startsWith("-")) {
if (args[i].equalsIgnoreCase("-path") && (i + 1 < args.length)) {
path = args[i + 1];
i += 2;
} else if (args[i].equalsIgnoreCase("-train") && (i + 2 < args.length)) {
trainLow = Integer.parseInt(args[i + 1]);
trainHigh = Integer.parseInt(args[i + 2]);
i += 3;
} else if (args[i].equalsIgnoreCase("-test") && (i + 2 < args.length)) {
testLow = Integer.parseInt(args[i + 1]);
testHigh = Integer.parseInt(args[i + 2]);
i += 3;
} else if (args[i].equalsIgnoreCase("-serialize") && (i + 1 < args.length)) {
serializeFile = args[i + 1];
i += 2;
} else if (args[i].equalsIgnoreCase("-tLPP") && (i + 1 < args.length)) {
try {
op.tlpParams = (TreebankLangParserParams) Class.forName(args[i + 1]).newInstance();
} catch (ClassNotFoundException e) {
System.err.println("Class not found: " + args[i + 1]);
throw new RuntimeException(e);
} catch (InstantiationException e) {
System.err.println("Couldn't instantiate: " + args[i + 1] + ": " + e.toString());
throw new RuntimeException(e);
} catch (IllegalAccessException e) {
System.err.println("illegal access" + e);
throw new RuntimeException(e);
}
i += 2;
} else if (args[i].equals("-encoding")) {
// sets encoding for TreebankLangParserParams
op.tlpParams.setInputEncoding(args[i + 1]);
op.tlpParams.setOutputEncoding(args[i + 1]);
i += 2;
} else {
i = op.setOptionOrWarn(args, i);
}
}
// System.out.println(tlpParams.getClass());
TreebankLanguagePack tlp = op.tlpParams.treebankLanguagePack();
op.trainOptions.sisterSplitters =
new HashSet<String>(Arrays.asList(op.tlpParams.sisterSplitters()));
// BinarizerFactory.TreeAnnotator.setTreebankLang(tlpParams);
PrintWriter pw = op.tlpParams.pw();
op.testOptions.display();
op.trainOptions.display();
op.display();
op.tlpParams.display();
// setup tree transforms
Treebank trainTreebank = op.tlpParams.memoryTreebank();
MemoryTreebank testTreebank = op.tlpParams.testMemoryTreebank();
// Treebank blippTreebank = ((EnglishTreebankParserParams) tlpParams).diskTreebank();
// String blippPath = "/afs/ir.stanford.edu/data/linguistic-data/BLLIP-WSJ/";
// blippTreebank.loadPath(blippPath, "", true);
Timing.startTime();
System.err.print("Reading trees...");
testTreebank.loadPath(path, new NumberRangeFileFilter(testLow, testHigh, true));
if (op.testOptions.increasingLength) {
Collections.sort(testTreebank, new TreeLengthComparator());
}
trainTreebank.loadPath(path, new NumberRangeFileFilter(trainLow, trainHigh, true));
Timing.tick("done.");
System.err.print("Binarizing trees...");
TreeAnnotatorAndBinarizer binarizer;
if (!op.trainOptions.leftToRight) {
binarizer =
new TreeAnnotatorAndBinarizer(
op.tlpParams, op.forceCNF, !op.trainOptions.outsideFactor(), true, op);
} else {
binarizer =
new TreeAnnotatorAndBinarizer(
op.tlpParams.headFinder(),
new LeftHeadFinder(),
op.tlpParams,
op.forceCNF,
!op.trainOptions.outsideFactor(),
true,
op);
}
CollinsPuncTransformer collinsPuncTransformer = null;
if (op.trainOptions.collinsPunc) {
collinsPuncTransformer = new CollinsPuncTransformer(tlp);
}
TreeTransformer debinarizer = new Debinarizer(op.forceCNF);
List<Tree> binaryTrainTrees = new ArrayList<Tree>();
if (op.trainOptions.selectiveSplit) {
op.trainOptions.splitters =
ParentAnnotationStats.getSplitCategories(
trainTreebank,
op.trainOptions.tagSelectiveSplit,
0,
op.trainOptions.selectiveSplitCutOff,
op.trainOptions.tagSelectiveSplitCutOff,
op.tlpParams.treebankLanguagePack());
if (op.trainOptions.deleteSplitters != null) {
List<String> deleted = new ArrayList<String>();
for (String del : op.trainOptions.deleteSplitters) {
String baseDel = tlp.basicCategory(del);
boolean checkBasic = del.equals(baseDel);
for (Iterator<String> it = op.trainOptions.splitters.iterator(); it.hasNext(); ) {
String elem = it.next();
String baseElem = tlp.basicCategory(elem);
boolean delStr = checkBasic && baseElem.equals(baseDel) || elem.equals(del);
if (delStr) {
it.remove();
deleted.add(elem);
}
}
}
System.err.println("Removed from vertical splitters: " + deleted);
}
}
if (op.trainOptions.selectivePostSplit) {
TreeTransformer myTransformer =
new TreeAnnotator(op.tlpParams.headFinder(), op.tlpParams, op);
Treebank annotatedTB = trainTreebank.transform(myTransformer);
op.trainOptions.postSplitters =
ParentAnnotationStats.getSplitCategories(
annotatedTB,
true,
0,
op.trainOptions.selectivePostSplitCutOff,
op.trainOptions.tagSelectivePostSplitCutOff,
op.tlpParams.treebankLanguagePack());
}
if (op.trainOptions.hSelSplit) {
binarizer.setDoSelectiveSplit(false);
for (Tree tree : trainTreebank) {
if (op.trainOptions.collinsPunc) {
tree = collinsPuncTransformer.transformTree(tree);
}
// tree.pennPrint(tlpParams.pw());
tree = binarizer.transformTree(tree);
// binaryTrainTrees.add(tree);
}
binarizer.setDoSelectiveSplit(true);
}
for (Tree tree : trainTreebank) {
if (op.trainOptions.collinsPunc) {
tree = collinsPuncTransformer.transformTree(tree);
}
tree = binarizer.transformTree(tree);
binaryTrainTrees.add(tree);
}
if (op.testOptions.verbose) {
binarizer.dumpStats();
}
List<Tree> binaryTestTrees = new ArrayList<Tree>();
for (Tree tree : testTreebank) {
if (op.trainOptions.collinsPunc) {
tree = collinsPuncTransformer.transformTree(tree);
}
tree = binarizer.transformTree(tree);
binaryTestTrees.add(tree);
}
Timing.tick("done."); // binarization
BinaryGrammar bg = null;
UnaryGrammar ug = null;
DependencyGrammar dg = null;
// DependencyGrammar dgBLIPP = null;
Lexicon lex = null;
Index<String> stateIndex = new HashIndex<String>();
// extract grammars
Extractor<Pair<UnaryGrammar, BinaryGrammar>> bgExtractor =
new BinaryGrammarExtractor(op, stateIndex);
// Extractor bgExtractor = new SmoothedBinaryGrammarExtractor();//new BinaryGrammarExtractor();
// Extractor lexExtractor = new LexiconExtractor();
// Extractor dgExtractor = new DependencyMemGrammarExtractor();
if (op.doPCFG) {
System.err.print("Extracting PCFG...");
Pair<UnaryGrammar, BinaryGrammar> bgug = null;
if (op.trainOptions.cheatPCFG) {
List<Tree> allTrees = new ArrayList<Tree>(binaryTrainTrees);
allTrees.addAll(binaryTestTrees);
bgug = bgExtractor.extract(allTrees);
} else {
bgug = bgExtractor.extract(binaryTrainTrees);
}
bg = bgug.second;
bg.splitRules();
ug = bgug.first;
ug.purgeRules();
Timing.tick("done.");
}
System.err.print("Extracting Lexicon...");
Index<String> wordIndex = new HashIndex<String>();
Index<String> tagIndex = new HashIndex<String>();
lex = op.tlpParams.lex(op, wordIndex, tagIndex);
lex.train(binaryTrainTrees);
Timing.tick("done.");
if (op.doDep) {
System.err.print("Extracting Dependencies...");
binaryTrainTrees.clear();
Extractor<DependencyGrammar> dgExtractor =
new MLEDependencyGrammarExtractor(op, wordIndex, tagIndex);
// dgBLIPP = (DependencyGrammar) dgExtractor.extract(new
// ConcatenationIterator(trainTreebank.iterator(),blippTreebank.iterator()),new
// TransformTreeDependency(tlpParams,true));
// DependencyGrammar dg1 = dgExtractor.extract(trainTreebank.iterator(), new
// TransformTreeDependency(op.tlpParams, true));
// dgBLIPP=(DependencyGrammar)dgExtractor.extract(blippTreebank.iterator(),new
// TransformTreeDependency(tlpParams));
// dg = (DependencyGrammar) dgExtractor.extract(new
// ConcatenationIterator(trainTreebank.iterator(),blippTreebank.iterator()),new
// TransformTreeDependency(tlpParams));
// dg=new DependencyGrammarCombination(dg1,dgBLIPP,2);
dg =
dgExtractor.extract(
binaryTrainTrees); // uses information whether the words are known or not, discards
// unknown words
Timing.tick("done.");
// System.out.print("Extracting Unknown Word Model...");
// UnknownWordModel uwm = (UnknownWordModel)uwmExtractor.extract(binaryTrainTrees);
// Timing.tick("done.");
System.out.print("Tuning Dependency Model...");
dg.tune(binaryTestTrees);
// System.out.println("TUNE DEPS: "+tuneDeps);
Timing.tick("done.");
}
BinaryGrammar boundBG = bg;
UnaryGrammar boundUG = ug;
GrammarProjection gp = new NullGrammarProjection(bg, ug);
// serialization
if (serializeFile != null) {
System.err.print("Serializing parser...");
LexicalizedParser.saveParserDataToSerialized(
new ParserData(lex, bg, ug, dg, stateIndex, wordIndex, tagIndex, op), serializeFile);
Timing.tick("done.");
}
// test: pcfg-parse and output
ExhaustivePCFGParser parser = null;
if (op.doPCFG) {
parser = new ExhaustivePCFGParser(boundBG, boundUG, lex, op, stateIndex, wordIndex, tagIndex);
}
ExhaustiveDependencyParser dparser =
((op.doDep && !op.testOptions.useFastFactored)
? new ExhaustiveDependencyParser(dg, lex, op, wordIndex, tagIndex)
: null);
Scorer scorer =
(op.doPCFG ? new TwinScorer(new ProjectionScorer(parser, gp, op), dparser) : null);
// Scorer scorer = parser;
BiLexPCFGParser bparser = null;
if (op.doPCFG && op.doDep) {
bparser =
(op.testOptions.useN5)
? new BiLexPCFGParser.N5BiLexPCFGParser(
scorer, parser, dparser, bg, ug, dg, lex, op, gp, stateIndex, wordIndex, tagIndex)
: new BiLexPCFGParser(
scorer,
parser,
dparser,
bg,
ug,
dg,
lex,
op,
gp,
stateIndex,
wordIndex,
tagIndex);
}
Evalb pcfgPE = new Evalb("pcfg PE", true);
Evalb comboPE = new Evalb("combo PE", true);
AbstractEval pcfgCB = new Evalb.CBEval("pcfg CB", true);
AbstractEval pcfgTE = new TaggingEval("pcfg TE");
AbstractEval comboTE = new TaggingEval("combo TE");
AbstractEval pcfgTEnoPunct = new TaggingEval("pcfg nopunct TE");
AbstractEval comboTEnoPunct = new TaggingEval("combo nopunct TE");
AbstractEval depTE = new TaggingEval("depnd TE");
AbstractEval depDE =
new UnlabeledAttachmentEval("depnd DE", true, null, tlp.punctuationWordRejectFilter());
AbstractEval comboDE =
new UnlabeledAttachmentEval("combo DE", true, null, tlp.punctuationWordRejectFilter());
if (op.testOptions.evalb) {
EvalbFormatWriter.initEVALBfiles(op.tlpParams);
}
// int[] countByLength = new int[op.testOptions.maxLength+1];
// Use a reflection ruse, so one can run this without needing the
// tagger. Using a function rather than a MaxentTagger means we
// can distribute a version of the parser that doesn't include the
// entire tagger.
Function<List<? extends HasWord>, ArrayList<TaggedWord>> tagger = null;
if (op.testOptions.preTag) {
try {
Class[] argsClass = {String.class};
Object[] arguments = new Object[] {op.testOptions.taggerSerializedFile};
tagger =
(Function<List<? extends HasWord>, ArrayList<TaggedWord>>)
Class.forName("edu.stanford.nlp.tagger.maxent.MaxentTagger")
.getConstructor(argsClass)
.newInstance(arguments);
} catch (Exception e) {
System.err.println(e);
System.err.println("Warning: No pretagging of sentences will be done.");
}
}
for (int tNum = 0, ttSize = testTreebank.size(); tNum < ttSize; tNum++) {
Tree tree = testTreebank.get(tNum);
int testTreeLen = tree.yield().size();
if (testTreeLen > op.testOptions.maxLength) {
continue;
}
Tree binaryTree = binaryTestTrees.get(tNum);
// countByLength[testTreeLen]++;
System.out.println("-------------------------------------");
System.out.println("Number: " + (tNum + 1));
System.out.println("Length: " + testTreeLen);
// tree.pennPrint(pw);
// System.out.println("XXXX The binary tree is");
// binaryTree.pennPrint(pw);
// System.out.println("Here are the tags in the lexicon:");
// System.out.println(lex.showTags());
// System.out.println("Here's the tagnumberer:");
// System.out.println(Numberer.getGlobalNumberer("tags").toString());
long timeMil1 = System.currentTimeMillis();
Timing.tick("Starting parse.");
if (op.doPCFG) {
// System.err.println(op.testOptions.forceTags);
if (op.testOptions.forceTags) {
if (tagger != null) {
// System.out.println("Using a tagger to set tags");
// System.out.println("Tagged sentence as: " +
// tagger.processSentence(cutLast(wordify(binaryTree.yield()))).toString(false));
parser.parse(addLast(tagger.apply(cutLast(wordify(binaryTree.yield())))));
} else {
// System.out.println("Forcing tags to match input.");
parser.parse(cleanTags(binaryTree.taggedYield(), tlp));
}
} else {
// System.out.println("XXXX Parsing " + binaryTree.yield());
parser.parse(binaryTree.yieldHasWord());
}
// Timing.tick("Done with pcfg phase.");
}
if (op.doDep) {
dparser.parse(binaryTree.yieldHasWord());
// Timing.tick("Done with dependency phase.");
}
boolean bothPassed = false;
if (op.doPCFG && op.doDep) {
bothPassed = bparser.parse(binaryTree.yieldHasWord());
// Timing.tick("Done with combination phase.");
}
long timeMil2 = System.currentTimeMillis();
long elapsed = timeMil2 - timeMil1;
System.err.println("Time: " + ((int) (elapsed / 100)) / 10.00 + " sec.");
// System.out.println("PCFG Best Parse:");
Tree tree2b = null;
Tree tree2 = null;
// System.out.println("Got full best parse...");
if (op.doPCFG) {
tree2b = parser.getBestParse();
tree2 = debinarizer.transformTree(tree2b);
}
// System.out.println("Debinarized parse...");
// tree2.pennPrint();
// System.out.println("DepG Best Parse:");
Tree tree3 = null;
Tree tree3db = null;
if (op.doDep) {
tree3 = dparser.getBestParse();
// was: but wrong Tree tree3db = debinarizer.transformTree(tree2);
tree3db = debinarizer.transformTree(tree3);
tree3.pennPrint(pw);
}
// tree.pennPrint();
// ((Tree)binaryTrainTrees.get(tNum)).pennPrint();
// System.out.println("Combo Best Parse:");
Tree tree4 = null;
if (op.doPCFG && op.doDep) {
try {
tree4 = bparser.getBestParse();
if (tree4 == null) {
tree4 = tree2b;
}
} catch (NullPointerException e) {
System.err.println("Blocked, using PCFG parse!");
tree4 = tree2b;
}
}
if (op.doPCFG && !bothPassed) {
tree4 = tree2b;
}
// tree4.pennPrint();
if (op.doDep) {
depDE.evaluate(tree3, binaryTree, pw);
depTE.evaluate(tree3db, tree, pw);
}
TreeTransformer tc = op.tlpParams.collinizer();
TreeTransformer tcEvalb = op.tlpParams.collinizerEvalb();
if (op.doPCFG) {
// System.out.println("XXXX Best PCFG was: ");
// tree2.pennPrint();
// System.out.println("XXXX Transformed best PCFG is: ");
// tc.transformTree(tree2).pennPrint();
// System.out.println("True Best Parse:");
// tree.pennPrint();
// tc.transformTree(tree).pennPrint();
pcfgPE.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);
pcfgCB.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);
Tree tree4b = null;
if (op.doDep) {
comboDE.evaluate((bothPassed ? tree4 : tree3), binaryTree, pw);
tree4b = tree4;
tree4 = debinarizer.transformTree(tree4);
if (op.nodePrune) {
NodePruner np = new NodePruner(parser, debinarizer);
tree4 = np.prune(tree4);
}
// tree4.pennPrint();
comboPE.evaluate(tc.transformTree(tree4), tc.transformTree(tree), pw);
}
// pcfgTE.evaluate(tree2, tree);
pcfgTE.evaluate(tcEvalb.transformTree(tree2), tcEvalb.transformTree(tree), pw);
pcfgTEnoPunct.evaluate(tc.transformTree(tree2), tc.transformTree(tree), pw);
if (op.doDep) {
comboTE.evaluate(tcEvalb.transformTree(tree4), tcEvalb.transformTree(tree), pw);
comboTEnoPunct.evaluate(tc.transformTree(tree4), tc.transformTree(tree), pw);
}
System.out.println("PCFG only: " + parser.scoreBinarizedTree(tree2b, 0));
// tc.transformTree(tree2).pennPrint();
tree2.pennPrint(pw);
if (op.doDep) {
System.out.println("Combo: " + parser.scoreBinarizedTree(tree4b, 0));
// tc.transformTree(tree4).pennPrint(pw);
tree4.pennPrint(pw);
}
System.out.println("Correct:" + parser.scoreBinarizedTree(binaryTree, 0));
/*
if (parser.scoreBinarizedTree(tree2b,true) < parser.scoreBinarizedTree(binaryTree,true)) {
System.out.println("SCORE INVERSION");
parser.validateBinarizedTree(binaryTree,0);
}
*/
tree.pennPrint(pw);
} // end if doPCFG
if (op.testOptions.evalb) {
if (op.doPCFG && op.doDep) {
EvalbFormatWriter.writeEVALBline(
tcEvalb.transformTree(tree), tcEvalb.transformTree(tree4));
} else if (op.doPCFG) {
EvalbFormatWriter.writeEVALBline(
tcEvalb.transformTree(tree), tcEvalb.transformTree(tree2));
} else if (op.doDep) {
EvalbFormatWriter.writeEVALBline(
tcEvalb.transformTree(tree), tcEvalb.transformTree(tree3db));
}
}
} // end for each tree in test treebank
if (op.testOptions.evalb) {
EvalbFormatWriter.closeEVALBfiles();
}
// op.testOptions.display();
if (op.doPCFG) {
pcfgPE.display(false, pw);
System.out.println("Grammar size: " + stateIndex.size());
pcfgCB.display(false, pw);
if (op.doDep) {
comboPE.display(false, pw);
}
pcfgTE.display(false, pw);
pcfgTEnoPunct.display(false, pw);
if (op.doDep) {
comboTE.display(false, pw);
comboTEnoPunct.display(false, pw);
}
}
if (op.doDep) {
depTE.display(false, pw);
depDE.display(false, pw);
}
if (op.doPCFG && op.doDep) {
comboDE.display(false, pw);
}
// pcfgPE.printGoodBad();
}
/**
* Usage: java edu.stanford.nlp.trees.tregex.tsurgeon.Tsurgeon [-s] -treeFile file-with-trees [-po
* matching-pattern operation] operation-file-1 operation-file-2 ... operation-file-n
*
* <h4>Arguments:</h4>
*
* Each argument should be the name of a transformation file that contains a list of pattern and
* transformation operation list pairs. That is, it is a sequence of pairs of a {@link
* TregexPattern} pattern on one or more lines, then a blank line (empty or whitespace), then a
* list of transformation operations one per line (as specified by <b>Legal operation syntax</b>
* below) to apply when the pattern is matched, and then another blank line (empty or whitespace).
* Note the need for blank lines: The code crashes if they are not present as separators (although
* the blank line at the end of the file can be omitted). The script file can include comment
* lines, either whole comment lines or trailing comments introduced by %, which extend to the end
* of line. A needed percent mark can be escaped by a preceding backslash.
*
* <p>For example, if you want to excise an SBARQ node whenever it is the parent of an SQ node,
* and relabel the SQ node to S, your transformation file would look like this:
*
* <blockquote>
*
* <code>
* SBARQ=n1 < SQ=n2<br>
* <br>
* excise n1 n1<br>
* relabel n2 S
* </code>
*
* </blockquote>
*
* <p>
*
* <h4>Options:</h4>
*
* <ul>
* <li><code>-treeFile <filename></code> specify the name of the file that has the trees
* you want to transform.
* <li><code>-po <matchPattern> <operation></code> Apply a single operation to
* every tree using the specified match pattern and the specified operation. Use this option
* when you want to quickly try the effect of one pattern/surgery combination, and are too
* lazy to write a transformation file.
* <li><code>-s</code> Print each output tree on one line (default is pretty-printing).
* <li><code>-m</code> For every tree that had a matching pattern, print "before" (prepended as
* "Operated on:") and "after" (prepended as "Result:"). Unoperated trees just pass through
* the transducer as usual.
* <li><code>-encoding X</code> Uses character set X for input and output of trees.
* <li><code>-macros <filename></code> A file of macros to use on the tregex pattern.
* Macros should be one per line, with original and replacement separated by tabs.
* <li><code>-hf <headfinder-class-name></code> use the specified {@link HeadFinder} class
* to determine headship relations.
* <li><code>-hfArg <string></code> pass a string argument in to the {@link HeadFinder}
* class's constructor. <code>-hfArg</code> can be used multiple times to pass in multiple
* arguments.
* <li><code>-trf <TreeReaderFactory-class-name></code> use the specified {@link
* TreeReaderFactory} class to read trees from files.
* </ul>
*
* <h4>Legal operation syntax:</h4>
*
* <ul>
* <li><code>delete <name></code> deletes the node and everything below it.
* <li><code>prune <name></code> Like delete, but if, after the pruning, the parent has
* no children anymore, the parent is pruned too. Pruning continues to affect all ancestors
* until one is found with remaining children. This may result in a null tree.
* <li><code>excise <name1> <name2></code> The name1 node should either dominate
* or be the same as the name2 node. This excises out everything from name1 to name2. All
* the children of name2 go into the parent of name1, where name1 was.
* <li><code>relabel <name> <new-label></code> Relabels the node to have the new
* label. <br>
* There are three possible forms: <br>
* <code>relabel nodeX VP</code> - for changing a node label to an alphanumeric string <br>
* <code>relabel nodeX /''/</code> - for relabeling a node to something that isn't a valid
* identifier without quoting <br>
* <code>relabel nodeX /^VB(.*)$/verb\\/$1/</code> - for regular expression based
* relabeling. In this case, all matches of the regular expression against the node label
* are replaced with the replacement String. This has the semantics of Java/Perl's
* replaceAll: you may use capturing groups and put them in replacements with $n. For
* example, if the pattern is /foo/bar/ and the node matched is "foo", the replaceAll
* semantics result in "barbar". If the pattern is /^foo(.*)$/bar$1/ and node matched is
* "foofoo", relabel will result in "barfoo". <br>
* When using the regex replacement method, you can also use the sequences ={node} and
* %{var} in the replacement string to use captured nodes or variable strings in the
* replacement string. For example, if the Tregex pattern was "duck=bar" and the relabel is
* /foo/={bar}/, "foofoo" will be replaced with "duckduck". <br>
* To concatenate two nodes named in the tregex pattern, for example, you can use the
* pattern /^.*$/={foo}={bar}/. Note that the ^.*$ is necessary to make sure the regex
* pattern only matches and replaces once on the entire node name. <br>
* To get an "=" or a "%" in the replacement, using \ escaping. Also, as in the example you
* can escape a slash in the middle of the second and third forms with \\/ and \\\\. <br>
* <li><code>insert <name> <position></code> or <code>
* insert <tree> <position></code> inserts the named node or tree into the
* position specified.
* <li><code>move <name> <position></code> moves the named node into the
* specified position.
* <p>Right now the only ways to specify position are:
* <p><code>$+ <name></code> the left sister of the named node<br>
* <code>$- <name></code> the right sister of the named node<br>
* <code>>i <name></code> the i_th daughter of the named node<br>
* <code>>-i <name></code> the i_th daughter, counting from the right, of the
* named node.
* <li><code>replace <name1> <name2></code> deletes name1 and inserts a copy of
* name2 in its place.
* <li><code>replace <name> <tree> <tree2>...</code> deletes name and
* inserts the new tree(s) in its place. If more than one replacement tree is given, each of
* the new subtrees will be added in order where the old tree was. Multiple subtrees at the
* root is an illegal operation and will throw an exception.
* <li>{@code createSubtree <new-label> <name1> [<name2>]} Create a subtree out of all the nodes
* from {@code <name1>} through {@code <name2>} and puts the new subtree where that span
* used to be. To limit the operation to just one node, elide {@code <name2>}.
* <li><code>adjoin <auxiliary_tree> <name></code> Adjoins the specified auxiliary
* tree into the named node. The daughters of the target node will become the daughters of
* the foot of the auxiliary tree.
* <li><code>adjoinH <auxiliary_tree> <name></code> Similar to adjoin, but
* preserves the target node and makes it the root of <tree>. (It is still accessible
* as <code>name</code>. The root of the auxiliary tree is ignored.)
* <li><code>adjoinF <auxiliary_tree> <name></code> Similar to adjoin, but
* preserves the target node and makes it the foot of <tree>. (It is still accessible
* as <code>name</code>, and retains its status as parent of its children. The root of the
* auxiliary tree is ignored.)
* <li>
* <dt><code>coindex <name1> <name2> ... <nameM> </code> Puts a (Penn
* Treebank style) coindexation suffix of the form "-N" on each of nodes name_1 through
* name_m. The value of N will be automatically generated in reference to the existing
* coindexations in the tree, so that there is never an accidental clash of indices across
* things that are not meant to be coindexed.
* </ul>
*
* <p>In the context of <code>adjoin</code>, <code>adjoinH</code>, and <code>adjoinF</code>, an
* auxiliary tree is a tree in Penn Treebank format with <code>@</code> on exactly one of the
* leaves denoting the foot of the tree. The operations which use the foot use the labeled node.
* For example: <br>
* Tsurgeon: <code>adjoin (FOO (BAR@)) foo</code> <br>
* Tregex: <code>B=foo</code> <br>
* Input: <code>(A (B 1 2))</code> Output: <code>(A (FOO (BAR 1 2)))</code>
*
* <p>Tsurgeon applies the same operation to the same tree for as long as the given tregex
* operation matches. This means that infinite loops are very easy to cause. One common situation
* where this comes up is with an insert operation will repeats infinitely many times unless you
* add an expression to the tregex that matches against the inserted pattern. For example, this
* pattern will infinite loop:
*
* <blockquote>
*
* <code>
* TregexPattern tregex = TregexPattern.compile("S=node << NP"); <br>
* TsurgeonPattern tsurgeon = Tsurgeon.parseOperation("insert (NP foo) >-1 node");
* </code>
*
* </blockquote>
*
* This pattern, though, will terminate:
*
* <blockquote>
*
* <code>
* TregexPattern tregex = TregexPattern.compile("S=node << NP !<< foo"); <br>
* TsurgeonPattern tsurgeon = Tsurgeon.parseOperation("insert (NP foo) >-1 node");
* </code>
*
* </blockquote>
*
* <p>Tsurgeon has (very) limited support for conditional statements. If a pattern is prefaced
* with <code>if exists <name></code>, the rest of the pattern will only execute if the
* named node was found in the corresponding TregexMatcher.
*
* @param args a list of names of files each of which contains a single tregex matching pattern
* plus a list, one per line, of transformation operations to apply to the matched pattern.
* @throws Exception If an I/O or pattern syntax error
*/
public static void main(String[] args) throws Exception {
String headFinderClassName = null;
String headFinderOption = "-hf";
String[] headFinderArgs = null;
String headFinderArgOption = "-hfArg";
String encoding = "UTF-8";
String encodingOption = "-encoding";
if (args.length == 0) {
System.err.println(
"Usage: java edu.stanford.nlp.trees.tregex.tsurgeon.Tsurgeon [-s] -treeFile <file-with-trees> [-po <matching-pattern> <operation>] <operation-file-1> <operation-file-2> ... <operation-file-n>");
System.exit(0);
}
String treePrintFormats;
String singleLineOption = "-s";
String verboseOption = "-v";
String matchedOption =
"-m"; // if set, then print original form of trees that are matched & thus operated on
String patternOperationOption = "-po";
String treeFileOption = "-treeFile";
String trfOption = "-trf";
String macroOption = "-macros";
String macroFilename = "";
Map<String, Integer> flagMap = Generics.newHashMap();
flagMap.put(patternOperationOption, 2);
flagMap.put(treeFileOption, 1);
flagMap.put(trfOption, 1);
flagMap.put(singleLineOption, 0);
flagMap.put(encodingOption, 1);
flagMap.put(headFinderOption, 1);
flagMap.put(macroOption, 1);
Map<String, String[]> argsMap = StringUtils.argsToMap(args, flagMap);
args = argsMap.get(null);
if (argsMap.containsKey(headFinderOption))
headFinderClassName = argsMap.get(headFinderOption)[0];
if (argsMap.containsKey(headFinderArgOption)) headFinderArgs = argsMap.get(headFinderArgOption);
if (argsMap.containsKey(verboseOption)) verbose = true;
if (argsMap.containsKey(singleLineOption)) treePrintFormats = "oneline,";
else treePrintFormats = "penn,";
if (argsMap.containsKey(encodingOption)) encoding = argsMap.get(encodingOption)[0];
if (argsMap.containsKey(macroOption)) macroFilename = argsMap.get(macroOption)[0];
TreePrint tp = new TreePrint(treePrintFormats, new PennTreebankLanguagePack());
PrintWriter pwOut = new PrintWriter(new OutputStreamWriter(System.out, encoding), true);
TreeReaderFactory trf;
if (argsMap.containsKey(trfOption)) {
String trfClass = argsMap.get(trfOption)[0];
trf = ReflectionLoading.loadByReflection(trfClass);
} else {
trf = new TregexPattern.TRegexTreeReaderFactory();
}
Treebank trees = new DiskTreebank(trf, encoding);
if (argsMap.containsKey(treeFileOption)) {
trees.loadPath(argsMap.get(treeFileOption)[0]);
}
List<Pair<TregexPattern, TsurgeonPattern>> ops =
new ArrayList<Pair<TregexPattern, TsurgeonPattern>>();
TregexPatternCompiler compiler;
if (headFinderClassName == null) {
compiler = new TregexPatternCompiler();
} else {
HeadFinder hf;
if (headFinderArgs == null) {
hf = ReflectionLoading.loadByReflection(headFinderClassName);
} else {
hf = ReflectionLoading.loadByReflection(headFinderClassName, (Object[]) headFinderArgs);
}
compiler = new TregexPatternCompiler(hf);
}
Macros.addAllMacros(compiler, macroFilename, encoding);
if (argsMap.containsKey(patternOperationOption)) {
TregexPattern matchPattern = compiler.compile(argsMap.get(patternOperationOption)[0]);
TsurgeonPattern p = parseOperation(argsMap.get(patternOperationOption)[1]);
ops.add(new Pair<TregexPattern, TsurgeonPattern>(matchPattern, p));
} else {
for (String arg : args) {
List<Pair<TregexPattern, TsurgeonPattern>> pairs =
getOperationsFromFile(arg, encoding, compiler);
for (Pair<TregexPattern, TsurgeonPattern> pair : pairs) {
if (verbose) {
System.err.println(pair.second());
}
ops.add(pair);
}
}
}
for (Tree t : trees) {
Tree original = t.deepCopy();
Tree result = processPatternsOnTree(ops, t);
if (argsMap.containsKey(matchedOption) && matchedOnTree) {
pwOut.println("Operated on: ");
displayTree(original, tp, pwOut);
pwOut.println("Result: ");
}
displayTree(result, tp, pwOut);
}
}
/**
* 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();
}
/** @param args */
public static void main(String[] args) {
if (args.length != 3) {
System.err.printf(
"Usage: java %s language filename features%n",
TreebankFactoredLexiconStats.class.getName());
System.exit(-1);
}
Language language = Language.valueOf(args[0]);
TreebankLangParserParams tlpp = language.params;
if (language.equals(Language.Arabic)) {
String[] options = {"-arabicFactored"};
tlpp.setOptionFlag(options, 0);
} else {
String[] options = {"-frenchFactored"};
tlpp.setOptionFlag(options, 0);
}
Treebank tb = tlpp.diskTreebank();
tb.loadPath(args[1]);
MorphoFeatureSpecification morphoSpec =
language.equals(Language.Arabic)
? new ArabicMorphoFeatureSpecification()
: new FrenchMorphoFeatureSpecification();
String[] features = args[2].trim().split(",");
for (String feature : features) {
morphoSpec.activate(MorphoFeatureType.valueOf(feature));
}
// Counters
Counter<String> wordTagCounter = new ClassicCounter<>(30000);
Counter<String> morphTagCounter = new ClassicCounter<>(500);
// Counter<String> signatureTagCounter = new ClassicCounter<String>();
Counter<String> morphCounter = new ClassicCounter<>(500);
Counter<String> wordCounter = new ClassicCounter<>(30000);
Counter<String> tagCounter = new ClassicCounter<>(300);
Counter<String> lemmaCounter = new ClassicCounter<>(25000);
Counter<String> lemmaTagCounter = new ClassicCounter<>(25000);
Counter<String> richTagCounter = new ClassicCounter<>(1000);
Counter<String> reducedTagCounter = new ClassicCounter<>(500);
Counter<String> reducedTagLemmaCounter = new ClassicCounter<>(500);
Map<String, Set<String>> wordLemmaMap = Generics.newHashMap();
TwoDimensionalIntCounter<String, String> lemmaReducedTagCounter =
new TwoDimensionalIntCounter<>(30000);
TwoDimensionalIntCounter<String, String> reducedTagTagCounter =
new TwoDimensionalIntCounter<>(500);
TwoDimensionalIntCounter<String, String> tagReducedTagCounter =
new TwoDimensionalIntCounter<>(300);
int numTrees = 0;
for (Tree tree : tb) {
for (Tree subTree : tree) {
if (!subTree.isLeaf()) {
tlpp.transformTree(subTree, tree);
}
}
List<Label> pretermList = tree.preTerminalYield();
List<Label> yield = tree.yield();
assert yield.size() == pretermList.size();
int yieldLen = yield.size();
for (int i = 0; i < yieldLen; ++i) {
String tag = pretermList.get(i).value();
String word = yield.get(i).value();
String morph = ((CoreLabel) yield.get(i)).originalText();
// Note: if there is no lemma, then we use the surface form.
Pair<String, String> lemmaTag = MorphoFeatureSpecification.splitMorphString(word, morph);
String lemma = lemmaTag.first();
String richTag = lemmaTag.second();
// WSGDEBUG
if (tag.contains("MW")) lemma += "-MWE";
lemmaCounter.incrementCount(lemma);
lemmaTagCounter.incrementCount(lemma + tag);
richTagCounter.incrementCount(richTag);
String reducedTag = morphoSpec.strToFeatures(richTag).toString();
reducedTagCounter.incrementCount(reducedTag);
reducedTagLemmaCounter.incrementCount(reducedTag + lemma);
wordTagCounter.incrementCount(word + tag);
morphTagCounter.incrementCount(morph + tag);
morphCounter.incrementCount(morph);
wordCounter.incrementCount(word);
tagCounter.incrementCount(tag);
reducedTag = reducedTag.equals("") ? "NONE" : reducedTag;
if (wordLemmaMap.containsKey(word)) {
wordLemmaMap.get(word).add(lemma);
} else {
Set<String> lemmas = Generics.newHashSet(1);
wordLemmaMap.put(word, lemmas);
}
lemmaReducedTagCounter.incrementCount(lemma, reducedTag);
reducedTagTagCounter.incrementCount(lemma + reducedTag, tag);
tagReducedTagCounter.incrementCount(tag, reducedTag);
}
++numTrees;
}
// Barf...
System.out.println("Language: " + language.toString());
System.out.printf("#trees:\t%d%n", numTrees);
System.out.printf("#tokens:\t%d%n", (int) wordCounter.totalCount());
System.out.printf("#words:\t%d%n", wordCounter.keySet().size());
System.out.printf("#tags:\t%d%n", tagCounter.keySet().size());
System.out.printf("#wordTagPairs:\t%d%n", wordTagCounter.keySet().size());
System.out.printf("#lemmas:\t%d%n", lemmaCounter.keySet().size());
System.out.printf("#lemmaTagPairs:\t%d%n", lemmaTagCounter.keySet().size());
System.out.printf("#feattags:\t%d%n", reducedTagCounter.keySet().size());
System.out.printf("#feattag+lemmas:\t%d%n", reducedTagLemmaCounter.keySet().size());
System.out.printf("#richtags:\t%d%n", richTagCounter.keySet().size());
System.out.printf("#richtag+lemma:\t%d%n", morphCounter.keySet().size());
System.out.printf("#richtag+lemmaTagPairs:\t%d%n", morphTagCounter.keySet().size());
// Extra
System.out.println("==================");
StringBuilder sbNoLemma = new StringBuilder();
StringBuilder sbMultLemmas = new StringBuilder();
for (Map.Entry<String, Set<String>> wordLemmas : wordLemmaMap.entrySet()) {
String word = wordLemmas.getKey();
Set<String> lemmas = wordLemmas.getValue();
if (lemmas.size() == 0) {
sbNoLemma.append("NO LEMMAS FOR WORD: " + word + "\n");
continue;
}
if (lemmas.size() > 1) {
sbMultLemmas.append("MULTIPLE LEMMAS: " + word + " " + setToString(lemmas) + "\n");
continue;
}
String lemma = lemmas.iterator().next();
Set<String> reducedTags = lemmaReducedTagCounter.getCounter(lemma).keySet();
if (reducedTags.size() > 1) {
System.out.printf("%s --> %s%n", word, lemma);
for (String reducedTag : reducedTags) {
int count = lemmaReducedTagCounter.getCount(lemma, reducedTag);
String posTags =
setToString(reducedTagTagCounter.getCounter(lemma + reducedTag).keySet());
System.out.printf("\t%s\t%d\t%s%n", reducedTag, count, posTags);
}
System.out.println();
}
}
System.out.println("==================");
System.out.println(sbNoLemma.toString());
System.out.println(sbMultLemmas.toString());
System.out.println("==================");
List<String> tags = new ArrayList<>(tagReducedTagCounter.firstKeySet());
Collections.sort(tags);
for (String tag : tags) {
System.out.println(tag);
Set<String> reducedTags = tagReducedTagCounter.getCounter(tag).keySet();
for (String reducedTag : reducedTags) {
int count = tagReducedTagCounter.getCount(tag, reducedTag);
// reducedTag = reducedTag.equals("") ? "NONE" : reducedTag;
System.out.printf("\t%s\t%d%n", reducedTag, count);
}
System.out.println();
}
System.out.println("==================");
}
