/** * Simple tree reading utility method. Given a tree formatted as a PTB string, returns a Tree made by a specific TreeFactory. */ public static Tree readTree(String ptbTreeString, TreeFactory treeFactory) { try { PennTreeReader ptr = new PennTreeReader(new StringReader(ptbTreeString), treeFactory); return ptr.readTree(); } catch (IOException ex) { throw new RuntimeException(ex); } }
@Override public TreeReader newTreeReader(Reader in) { return new PennTreeReader(new BufferedReader(in), new LabeledScoredTreeFactory(), tn); }
/** * An implementation of the <code>TreeReaderFactory</code> interface. * It creates a <code>TreeReader</code> which normalizes trees using * the <code>BobChrisTreeNormalizer</code>, and makes * <code>LabeledScoredTree</code> objects with * <code>CategoryWordTag</code> labels (unless otherwise specified on * construction). */ public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(lf), tm); } }
@Override public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, tf, tn, new PennTreebankTokenizer(in)); }
/** * Loads treebank data from first argument and prints it. * * @param args Array of command-line arguments: specifies a filename */ public static void main(String[] args) { try { TreeFactory tf = new LabeledScoredTreeFactory(); Reader r = new BufferedReader(new InputStreamReader(new FileInputStream(args[0]), "UTF-8")); TreeReader tr = new PennTreeReader(r, tf); Tree t = tr.readTree(); while (t != null) { System.out.println(t); System.out.println(); t = tr.readTree(); } r.close(); } catch (IOException ioe) { throw new RuntimeIOException(ioe); } }
/** * returns a MemoryTreebank appropriate to the testing treebank source */ @Override public MemoryTreebank testMemoryTreebank() { return new MemoryTreebank(in -> new PennTreeReader(in, new LabeledScoredTreeFactory(), new BobChrisTreeNormalizer(tlp))); }
@Override public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(), new NPTmpRetainingTreeNormalizer(NPTmpRetainingTreeNormalizer.TEMPORAL_ACL03PCFG, false, 0, true)); }
@Override public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(), new NPTmpRetainingTreeNormalizer()); }
public static List<Tree> getTrees(String path, int low, int high, int minLength, int maxLength) { Treebank treebank = new DiskTreebank(in -> new PennTreeReader(in, new LabeledScoredTreeFactory(new WordFactory()), new BobChrisTreeNormalizer())); treebank.loadPath(path, new NumberRangeFileFilter(low, high, true)); List<Tree> trees = new ArrayList<>(); for (Tree tree : treebank) { if (tree.yield().size() <= maxLength && tree.yield().size() >= minLength) { trees.add(tree); } } return trees; }
public static void main(String[] args) throws IOException { int i = 0; while (i < args.length) { Tree tree = Tree.valueOf(args[i]); if (tree == null) { // maybe it was a filename tree = Tree.valueOf(IOUtils.slurpFile(args[i])); } if (tree != null) { System.out.println(escape(texTree(tree))); } i++; } if (i == 0) { Tree tree = (new PennTreeReader(new BufferedReader(new InputStreamReader(System.in)), new LabeledScoredTreeFactory(new StringLabelFactory()))).readTree(); System.out.println(escape(texTree(tree))); } }
/** * Just for testing. */ public static void main(String[] args) { try { TreeReader tr = new PennTreeReader(new StringReader("(S (NP (NNP Sam)) (VP (VBD died) (NP (NN today))))"), new LabeledScoredTreeFactory()); Tree t = tr.readTree(); System.out.println(t); TreeGraphNode tgn = new TreeGraphNode(t, (TreeGraphNode) null); System.out.println(tgn.toPrettyString(0)); EnglishGrammaticalStructure gs = new EnglishGrammaticalStructure(tgn); System.out.println(tgn.toPrettyString(0)); tgn.percolateHeads(new SemanticHeadFinder()); System.out.println(tgn.toPrettyString(0)); } catch (Exception e) { log.error("Horrible error: " + e); log.error(e); } }
/** * Makes appropriate TreeReaderFactory with all options specified */ @Override public TreeReaderFactory treeReaderFactory() { return in -> new PennTreeReader(in, new LabeledScoredTreeFactory(), new NPTmpRetainingTreeNormalizer(englishTrain.splitTMP, englishTrain.splitSGapped == 5, englishTrain.leaveItAll, englishTrain.splitNPADV >= 1, headFinder())); }
/** * An implementation of the <code>TreeReaderFactory</code> interface. * It creates a simple <code>TreeReader</code> which literally * reproduces trees in the treebank as <code>LabeledScoredTree</code> * objects, with <code>StringLabel</code> labels. */ public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory())); }
public TreeReader newTreeReader(Reader in) { final TreeNormalizer tn1 = new GrammaticalFunctionTreeNormalizer(tlp, nodeCleanup); final TueBaDZPennTreeNormalizer tn2 = new TueBaDZPennTreeNormalizer(tlp, nodeCleanup); final TreeNormalizer norm = new OrderedCombinationTreeNormalizer(Arrays.asList(tn1, tn2)); return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), norm); }
public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(), new SpanishTreeNormalizer(false, false, false), new PennTreebankTokenizer(in)); }
@Override public TreeReader newTreeReader(Reader in) { final NegraPennTreeNormalizer tn = new NegraPennTreeNormalizer(tlp, nodeCleanup); if (treeNormalizerInsertNPinPP) tn.setInsertNPinPP(true); return new PennTreeReader(in, new LabeledScoredTreeFactory(), tn, new NegraPennTokenizer(in)); }
public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(), new FrenchTreeNormalizer(false), new PennTreebankTokenizer(in)); } }
public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(), new HebrewTreeNormalizer(),new PennTreebankTokenizer(in)); }
public TreeReader newTreeReader(Reader in) { TreeReader tr = null; if(noNormalization) { tr = new PennTreeReader(in, new LabeledScoredTreeFactory(), new TreeNormalizer(), new ArabicTreebankTokenizer(in)); } else tr = new PennTreeReader(in, new LabeledScoredTreeFactory(), new ArabicTreeNormalizer(retainNPTmp,retainPRD,changeNoLabels, retainNPSbj, retainPPClr), new ArabicTreebankTokenizer(in)); if (filterX) tr = new FilteringTreeReader(tr, new XFilter()); return tr; }
/** * Create a new {@code TreeReader} using the provided * {@code Reader}. * * @param in The {@code Reader} to build on * @return The new TreeReader */ @Override public TreeReader newTreeReader(Reader in) { if (discardFrags) { return new FragDiscardingPennTreeReader(in, new LabeledScoredTreeFactory(), tn, new CHTBTokenizer(in)); } else { return new PennTreeReader(in, new LabeledScoredTreeFactory(), tn, new CHTBTokenizer(in)); } }