public ParseEssay() {
System.setProperty("wordnet.database.dir", "../war/dict");
synonyms = new ArrayList<String>();
database = WordNetDatabase.getFileInstance();
baos = new ByteArrayOutputStream();
lp = LexicalizedParser.loadModel("edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz");
// ??
}
/**
* 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);
}
}
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("Currently " + new Date());
System.out.print("Invoked with arguments:");
for (String arg : args) {
System.out.print(" " + arg);
}
System.out.println();
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]);
} catch (InstantiationException e) {
System.err.println("Couldn't instantiate: " + args[i + 1] + ": " + e.toString());
} catch (IllegalAccessException e) {
System.err.println("illegal access" + 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();
Train.sisterSplitters = new HashSet(Arrays.asList(op.tlpParams.sisterSplitters()));
// BinarizerFactory.TreeAnnotator.setTreebankLang(tlpParams);
PrintWriter pw = op.tlpParams.pw();
Test.display();
Train.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 (Test.increasingLength) {
Collections.sort(testTreebank, new TreeLengthComparator());
}
trainTreebank.loadPath(path, new NumberRangeFileFilter(trainLow, trainHigh, true));
Timing.tick("done.");
System.err.print("Binarizing trees...");
TreeAnnotatorAndBinarizer binarizer = null;
if (!Train.leftToRight) {
binarizer =
new TreeAnnotatorAndBinarizer(op.tlpParams, op.forceCNF, !Train.outsideFactor(), true);
} else {
binarizer =
new TreeAnnotatorAndBinarizer(
op.tlpParams.headFinder(),
new LeftHeadFinder(),
op.tlpParams,
op.forceCNF,
!Train.outsideFactor(),
true);
}
CollinsPuncTransformer collinsPuncTransformer = null;
if (Train.collinsPunc) {
collinsPuncTransformer = new CollinsPuncTransformer(tlp);
}
TreeTransformer debinarizer = new Debinarizer(op.forceCNF);
List<Tree> binaryTrainTrees = new ArrayList<Tree>();
if (Train.selectiveSplit) {
Train.splitters =
ParentAnnotationStats.getSplitCategories(
trainTreebank,
Train.tagSelectiveSplit,
0,
Train.selectiveSplitCutOff,
Train.tagSelectiveSplitCutOff,
op.tlpParams.treebankLanguagePack());
if (Train.deleteSplitters != null) {
List<String> deleted = new ArrayList<String>();
for (String del : Train.deleteSplitters) {
String baseDel = tlp.basicCategory(del);
boolean checkBasic = del.equals(baseDel);
for (Iterator<String> it = Train.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 (Train.selectivePostSplit) {
TreeTransformer myTransformer = new TreeAnnotator(op.tlpParams.headFinder(), op.tlpParams);
Treebank annotatedTB = trainTreebank.transform(myTransformer);
Train.postSplitters =
ParentAnnotationStats.getSplitCategories(
annotatedTB,
true,
0,
Train.selectivePostSplitCutOff,
Train.tagSelectivePostSplitCutOff,
op.tlpParams.treebankLanguagePack());
}
if (Train.hSelSplit) {
binarizer.setDoSelectiveSplit(false);
for (Tree tree : trainTreebank) {
if (Train.collinsPunc) {
tree = collinsPuncTransformer.transformTree(tree);
}
// tree.pennPrint(tlpParams.pw());
tree = binarizer.transformTree(tree);
// binaryTrainTrees.add(tree);
}
binarizer.setDoSelectiveSplit(true);
}
for (Tree tree : trainTreebank) {
if (Train.collinsPunc) {
tree = collinsPuncTransformer.transformTree(tree);
}
tree = binarizer.transformTree(tree);
binaryTrainTrees.add(tree);
}
if (Test.verbose) {
binarizer.dumpStats();
}
List<Tree> binaryTestTrees = new ArrayList<Tree>();
for (Tree tree : testTreebank) {
if (Train.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;
// extract grammars
Extractor bgExtractor = new BinaryGrammarExtractor();
// Extractor bgExtractor = new SmoothedBinaryGrammarExtractor();//new BinaryGrammarExtractor();
// Extractor lexExtractor = new LexiconExtractor();
// Extractor dgExtractor = new DependencyMemGrammarExtractor();
Extractor dgExtractor = new MLEDependencyGrammarExtractor(op);
if (op.doPCFG) {
System.err.print("Extracting PCFG...");
Pair bgug = null;
if (Train.cheatPCFG) {
List allTrees = new ArrayList(binaryTrainTrees);
allTrees.addAll(binaryTestTrees);
bgug = (Pair) bgExtractor.extract(allTrees);
} else {
bgug = (Pair) bgExtractor.extract(binaryTrainTrees);
}
bg = (BinaryGrammar) bgug.second;
bg.splitRules();
ug = (UnaryGrammar) bgug.first;
ug.purgeRules();
Timing.tick("done.");
}
System.err.print("Extracting Lexicon...");
lex = op.tlpParams.lex(op.lexOptions);
lex.train(binaryTrainTrees);
Timing.tick("done.");
if (op.doDep) {
System.err.print("Extracting Dependencies...");
binaryTrainTrees.clear();
// dgBLIPP = (DependencyGrammar) dgExtractor.extract(new
// ConcatenationIterator(trainTreebank.iterator(),blippTreebank.iterator()),new
// TransformTreeDependency(tlpParams,true));
DependencyGrammar dg1 =
(DependencyGrammar)
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 = (DependencyGrammar) 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, Numberer.getNumberers(), op), serializeFile);
Timing.tick("done.");
}
// test: pcfg-parse and output
ExhaustivePCFGParser parser = null;
if (op.doPCFG) {
parser = new ExhaustivePCFGParser(boundBG, boundUG, lex, op);
}
ExhaustiveDependencyParser dparser =
((op.doDep && !Test.useFastFactored) ? new ExhaustiveDependencyParser(dg, lex, op) : null);
Scorer scorer = (op.doPCFG ? new TwinScorer(new ProjectionScorer(parser, gp), dparser) : null);
// Scorer scorer = parser;
BiLexPCFGParser bparser = null;
if (op.doPCFG && op.doDep) {
bparser =
(Test.useN5)
? new BiLexPCFGParser.N5BiLexPCFGParser(
scorer, parser, dparser, bg, ug, dg, lex, op, gp)
: new BiLexPCFGParser(scorer, parser, dparser, bg, ug, dg, lex, op, gp);
}
LabeledConstituentEval pcfgPE = new LabeledConstituentEval("pcfg PE", true, tlp);
LabeledConstituentEval comboPE = new LabeledConstituentEval("combo PE", true, tlp);
AbstractEval pcfgCB = new LabeledConstituentEval.CBEval("pcfg CB", true, tlp);
AbstractEval pcfgTE = new AbstractEval.TaggingEval("pcfg TE");
AbstractEval comboTE = new AbstractEval.TaggingEval("combo TE");
AbstractEval pcfgTEnoPunct = new AbstractEval.TaggingEval("pcfg nopunct TE");
AbstractEval comboTEnoPunct = new AbstractEval.TaggingEval("combo nopunct TE");
AbstractEval depTE = new AbstractEval.TaggingEval("depnd TE");
AbstractEval depDE =
new AbstractEval.DependencyEval("depnd DE", true, tlp.punctuationWordAcceptFilter());
AbstractEval comboDE =
new AbstractEval.DependencyEval("combo DE", true, tlp.punctuationWordAcceptFilter());
if (Test.evalb) {
EvalB.initEVALBfiles(op.tlpParams);
}
// int[] countByLength = new int[Test.maxLength+1];
// use a reflection ruse, so one can run this without needing the tagger
// edu.stanford.nlp.process.SentenceTagger tagger = (Test.preTag ? new
// edu.stanford.nlp.process.SentenceTagger("/u/nlp/data/tagger.params/wsj0-21.holder") : null);
SentenceProcessor tagger = null;
if (Test.preTag) {
try {
Class[] argsClass = new Class[] {String.class};
Object[] arguments =
new Object[] {"/u/nlp/data/pos-tagger/wsj3t0-18-bidirectional/train-wsj-0-18.holder"};
tagger =
(SentenceProcessor)
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 > Test.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(Test.forceTags);
if (Test.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.processSentence(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.yield());
}
// Timing.tick("Done with pcfg phase.");
}
if (op.doDep) {
dparser.parse(binaryTree.yield());
// Timing.tick("Done with dependency phase.");
}
boolean bothPassed = false;
if (op.doPCFG && op.doDep) {
bothPassed = bparser.parse(binaryTree.yield());
// 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();
Tree tree4b = null;
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);
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 (Test.evalb) {
if (op.doPCFG && op.doDep) {
EvalB.writeEVALBline(tcEvalb.transformTree(tree), tcEvalb.transformTree(tree4));
} else if (op.doPCFG) {
EvalB.writeEVALBline(tcEvalb.transformTree(tree), tcEvalb.transformTree(tree2));
} else if (op.doDep) {
EvalB.writeEVALBline(tcEvalb.transformTree(tree), tcEvalb.transformTree(tree3db));
}
}
} // end for each tree in test treebank
if (Test.evalb) {
EvalB.closeEVALBfiles();
}
// Test.display();
if (op.doPCFG) {
pcfgPE.display(false, pw);
System.out.println("Grammar size: " + Numberer.getGlobalNumberer("states").total());
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();
}
/**
* Prints out all matches of a tree pattern on each tree in the path. Usage: <br>
* <br>
* <code>
* java edu.stanford.nlp.trees.tregex.TregexPattern [[-TCwfosnu] [-filter] [-h <node-name>]]* pattern
* filepath </code>
*
* <p>Arguments:<br>
*
* <ul>
* <li><code>pattern</code>: the tree pattern which optionally names some set of nodes (i.e.,
* gives it the "handle") <code>=name</code> (for some arbitrary string "name")
* <li><code>filepath</code>: the path to files with trees. If this is a directory, there will
* be recursive descent and the pattern will be run on all files beneath the specified
* directory.
* </ul>
*
* <p>Options:<br>
* <li><code>-C</code> suppresses printing of matches, so only the number of matches is printed.
* <li><code>-w</code> causes the whole of a tree that matches to be printed.
* <li><code>-f</code> causes the filename to be printed.
* <li><code>-i <filename></code> causes the pattern to be matched to be read from <code>
* <filename></code> rather than the command line. Don't specify a pattern when this
* option is used.
* <li><code>-o</code> Specifies that each tree node can be reported only once as the root of a
* match (by default a node will be printed once for every <em>way</em> the pattern matches).
* <li><code>-s</code> causes trees to be printed all on one line (by default they are pretty
* printed).
* <li><code>-n</code> causes the number of the tree in which the match was found to be printed
* before every match.
* <li><code>-u</code> causes only the label of each matching node to be printed, not complete
* subtrees.
* <li><code>-t</code> causes only the yield (terminal words) of the selected node to be printed
* (or the yield of the whole tree, if the <code>-w</code> option is used).
* <li><code>-encoding <charset_encoding></code> option allows specification of character
* encoding of trees..
* <li><code>-h <node-handle></code> If a <code>-h</code> option is given, the root tree
* node will not be printed. Instead, for each <code>node-handle</code> specified, the node
* matched and given that handle will be printed. Multiple nodes can be printed by using the
* <code>-h</code> option multiple times on a single command line.
* <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.
* <li><code>-v</code> print every tree that contains no matches of the specified pattern, but
* print no matches to the pattern.
* <li><code>-x</code> Instead of the matched subtree, print the matched subtree's identifying
* number as defined in <tt>tgrep2</tt>:a unique identifier for the subtree and is in the form
* s:n, where s is an integer specifying the sentence number in the corpus (starting with 1),
* and n is an integer giving the order in which the node is encountered in a depth-first
* search starting with 1 at top node in the sentence tree.
* <li><code>-extract <code> <tree-file></code> extracts the subtree s:n specified by
* <tt>code</tt> from the specified <tt>tree-file</tt>. Overrides all other behavior of
* tregex. Can't specify multiple encodings etc. yet.
* <li><code>-extractFile <code-file> <tree-file></code> extracts every subtree
* specified by the subtree codes in <tt>code-file</tt>, which must appear exactly one per
* line, from the specified <tt>tree-file</tt>. Overrides all other behavior of tregex. Can't
* specify multiple encodings etc. yet.
* <li><code>-filter</code> causes this to act as a filter, reading tree input from stdin
* <li><code>-T</code> causes all trees to be printed as processed (for debugging purposes).
* Otherwise only matching nodes are printed.
* <li><code>-macros <filename></code> filename with macro substitutions to use. file with
* tab separated lines original-tab-replacement
* </ul>
*/
public static void main(String[] args) throws IOException {
Timing.startTime();
StringBuilder treePrintFormats = new StringBuilder();
String printNonMatchingTreesOption = "-v";
String subtreeCodeOption = "-x";
String extractSubtreesOption = "-extract";
String extractSubtreesFileOption = "-extractFile";
String inputFileOption = "-i";
String headFinderOption = "-hf";
String headFinderArgOption = "-hfArg";
String trfOption = "-trf";
String headFinderClassName = null;
String[] headFinderArgs = StringUtils.EMPTY_STRING_ARRAY;
String treeReaderFactoryClassName = null;
String printHandleOption = "-h";
String markHandleOption = "-k";
String encodingOption = "-encoding";
String encoding = "UTF-8";
String macroOption = "-macros";
String macroFilename = "";
String yieldOnly = "-t";
String printAllTrees = "-T";
String quietMode = "-C";
String wholeTreeMode = "-w";
String filenameOption = "-f";
String oneMatchPerRootNodeMode = "-o";
String reportTreeNumbers = "-n";
String rootLabelOnly = "-u";
String oneLine = "-s";
Map<String, Integer> flagMap = Generics.newHashMap();
flagMap.put(extractSubtreesOption, 2);
flagMap.put(extractSubtreesFileOption, 2);
flagMap.put(subtreeCodeOption, 0);
flagMap.put(printNonMatchingTreesOption, 0);
flagMap.put(encodingOption, 1);
flagMap.put(inputFileOption, 1);
flagMap.put(printHandleOption, 1);
flagMap.put(markHandleOption, 2);
flagMap.put(headFinderOption, 1);
flagMap.put(headFinderArgOption, 1);
flagMap.put(trfOption, 1);
flagMap.put(macroOption, 1);
flagMap.put(yieldOnly, 0);
flagMap.put(quietMode, 0);
flagMap.put(wholeTreeMode, 0);
flagMap.put(printAllTrees, 0);
flagMap.put(filenameOption, 0);
flagMap.put(oneMatchPerRootNodeMode, 0);
flagMap.put(reportTreeNumbers, 0);
flagMap.put(rootLabelOnly, 0);
flagMap.put(oneLine, 0);
Map<String, String[]> argsMap = StringUtils.argsToMap(args, flagMap);
args = argsMap.get(null);
if (argsMap.containsKey(encodingOption)) {
encoding = argsMap.get(encodingOption)[0];
System.err.println("Encoding set to " + encoding);
}
PrintWriter errPW = new PrintWriter(new OutputStreamWriter(System.err, encoding), true);
if (argsMap.containsKey(extractSubtreesOption)) {
List<String> subTreeStrings =
Collections.singletonList(argsMap.get(extractSubtreesOption)[0]);
extractSubtrees(subTreeStrings, argsMap.get(extractSubtreesOption)[1]);
return;
}
if (argsMap.containsKey(extractSubtreesFileOption)) {
List<String> subTreeStrings =
Arrays.asList(
IOUtils.slurpFile(argsMap.get(extractSubtreesFileOption)[0]).split("\n|\r|\n\r"));
extractSubtrees(subTreeStrings, argsMap.get(extractSubtreesFileOption)[0]);
return;
}
if (args.length < 1) {
errPW.println(
"Usage: java edu.stanford.nlp.trees.tregex.TregexPattern [-T] [-C] [-w] [-f] [-o] [-n] [-s] [-filter] [-hf class] [-trf class] [-h handle]* pattern [filepath]");
return;
}
String matchString = args[0];
if (argsMap.containsKey(macroOption)) {
macroFilename = argsMap.get(macroOption)[0];
}
if (argsMap.containsKey(headFinderOption)) {
headFinderClassName = argsMap.get(headFinderOption)[0];
errPW.println("Using head finder " + headFinderClassName + "...");
}
if (argsMap.containsKey(headFinderArgOption)) {
headFinderArgs = argsMap.get(headFinderArgOption);
}
if (argsMap.containsKey(trfOption)) {
treeReaderFactoryClassName = argsMap.get(trfOption)[0];
errPW.println("Using tree reader factory " + treeReaderFactoryClassName + "...");
}
if (argsMap.containsKey(printAllTrees)) {
TRegexTreeVisitor.printTree = true;
}
if (argsMap.containsKey(inputFileOption)) {
String inputFile = argsMap.get(inputFileOption)[0];
matchString = IOUtils.slurpFile(inputFile, encoding);
String[] newArgs = new String[args.length + 1];
System.arraycopy(args, 0, newArgs, 1, args.length);
args = newArgs;
}
if (argsMap.containsKey(quietMode)) {
TRegexTreeVisitor.printMatches = false;
TRegexTreeVisitor.printNumMatchesToStdOut = true;
}
if (argsMap.containsKey(printNonMatchingTreesOption)) {
TRegexTreeVisitor.printNonMatchingTrees = true;
}
if (argsMap.containsKey(subtreeCodeOption)) {
TRegexTreeVisitor.printSubtreeCode = true;
TRegexTreeVisitor.printMatches = false;
}
if (argsMap.containsKey(wholeTreeMode)) {
TRegexTreeVisitor.printWholeTree = true;
}
if (argsMap.containsKey(filenameOption)) {
TRegexTreeVisitor.printFilename = true;
}
if (argsMap.containsKey(oneMatchPerRootNodeMode)) TRegexTreeVisitor.oneMatchPerRootNode = true;
if (argsMap.containsKey(reportTreeNumbers)) TRegexTreeVisitor.reportTreeNumbers = true;
if (argsMap.containsKey(rootLabelOnly)) {
treePrintFormats.append(TreePrint.rootLabelOnlyFormat).append(',');
} else if (argsMap.containsKey(oneLine)) { // display short form
treePrintFormats.append("oneline,");
} else if (argsMap.containsKey(yieldOnly)) {
treePrintFormats.append("words,");
} else {
treePrintFormats.append("penn,");
}
HeadFinder hf = new CollinsHeadFinder();
if (headFinderClassName != null) {
Class[] hfArgClasses = new Class[headFinderArgs.length];
for (int i = 0; i < hfArgClasses.length; i++) hfArgClasses[i] = String.class;
try {
hf =
(HeadFinder)
Class.forName(headFinderClassName)
.getConstructor(hfArgClasses)
.newInstance(
(Object[])
headFinderArgs); // cast to Object[] necessary to avoid varargs-related
// warning.
} catch (Exception e) {
throw new RuntimeException("Error occurred while constructing HeadFinder: " + e);
}
}
TRegexTreeVisitor.tp =
new TreePrint(treePrintFormats.toString(), new PennTreebankLanguagePack());
try {
// TreePattern p = TreePattern.compile("/^S/ > S=dt $++ '' $-- ``");
TregexPatternCompiler tpc = new TregexPatternCompiler(hf);
Macros.addAllMacros(tpc, macroFilename, encoding);
TregexPattern p = tpc.compile(matchString);
errPW.println("Pattern string:\n" + p.pattern());
errPW.println("Parsed representation:");
p.prettyPrint(errPW);
String[] handles = argsMap.get(printHandleOption);
if (argsMap.containsKey("-filter")) {
TreeReaderFactory trf = getTreeReaderFactory(treeReaderFactoryClassName);
treebank =
new MemoryTreebank(
trf, encoding); // has to be in memory since we're not storing it on disk
// read from stdin
Reader reader = new BufferedReader(new InputStreamReader(System.in, encoding));
((MemoryTreebank) treebank).load(reader);
reader.close();
} else if (args.length == 1) {
errPW.println("using default tree");
TreeReader r =
new PennTreeReader(
new StringReader(
"(VP (VP (VBZ Try) (NP (NP (DT this) (NN wine)) (CC and) (NP (DT these) (NNS snails)))) (PUNCT .))"),
new LabeledScoredTreeFactory(new StringLabelFactory()));
Tree t = r.readTree();
treebank = new MemoryTreebank();
treebank.add(t);
} else {
int last = args.length - 1;
errPW.println("Reading trees from file(s) " + args[last]);
TreeReaderFactory trf = getTreeReaderFactory(treeReaderFactoryClassName);
treebank = new DiskTreebank(trf, encoding);
treebank.loadPath(args[last], null, true);
}
TRegexTreeVisitor vis = new TRegexTreeVisitor(p, handles, encoding);
treebank.apply(vis);
Timing.endTime();
if (TRegexTreeVisitor.printMatches) {
errPW.println("There were " + vis.numMatches() + " matches in total.");
}
if (TRegexTreeVisitor.printNumMatchesToStdOut) {
System.out.println(vis.numMatches());
}
} catch (IOException e) {
e.printStackTrace();
} catch (TregexParseException e) {
errPW.println("Error parsing expression: " + args[0]);
errPW.println("Parse exception: " + e.toString());
}
}