Examples with SpanishTreeReaderFactory edu.stanford.nlp.trees.international.spanish.SpanishTreeReaderFactory used on opensource projects

Example 1 with SpanishTreeReaderFactory

use of edu.stanford.nlp.trees.international.spanish.SpanishTreeReaderFactory in project CoreNLP by stanfordnlp.

the class MultiWordPreprocessor method main.

/**
   *
   * @param args
   */
public static void main(String[] args) {
    Properties options = StringUtils.argsToProperties(args, argOptionDefs);
    if (!options.containsKey("") || options.containsKey("help")) {
        log.info(usage());
        return;
    }
    boolean retainNER = PropertiesUtils.getBool(options, "ner", false);
    boolean normalize = PropertiesUtils.getBool(options, "normalize", true);
    final File treeFile = new File(options.getProperty(""));
    TwoDimensionalCounter<String, String> labelTerm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> termLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> labelPreterm = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> pretermLabel = new TwoDimensionalCounter<>();
    TwoDimensionalCounter<String, String> unigramTagger = new TwoDimensionalCounter<>();
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        for (Tree t; (t = tr.readTree()) != null; ) {
            updateTagger(unigramTagger, t);
        }
        //Closes the underlying reader
        tr.close();
        System.out.println("Resolving DUMMY tags");
        resolveDummyTags(treeFile, unigramTagger, retainNER, normalize ? new SpanishTreeNormalizer(true, false, false) : null);
        System.out.println("#Unknown Word Types: " + ManualUWModel.nUnknownWordTypes);
        System.out.println(String.format("#Missing POS: %d (fixed: %d, %.2f%%)", nMissingPOS, nFixedPOS, (double) nFixedPOS / nMissingPOS * 100));
        System.out.println(String.format("#Missing Phrasal: %d (fixed: %d, %.2f%%)", nMissingPhrasal, nFixedPhrasal, (double) nFixedPhrasal / nMissingPhrasal * 100));
        System.out.println("Done!");
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 2 with SpanishTreeReaderFactory

use of edu.stanford.nlp.trees.international.spanish.SpanishTreeReaderFactory in project CoreNLP by stanfordnlp.

the class TreeToTSV method main.

public static void main(String[] args) {
    if (args.length < 1) {
        System.err.printf("Usage: java %s tree_file%n", TreeToTSV.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        StringBuilder sb = new StringBuilder();
        String nl = System.getProperty("line.separator");
        Pattern nePattern = Pattern.compile("^grup\\.nom\\.");
        Pattern npPattern = Pattern.compile("^np0000.$");
        for (Tree tree; (tree = tr.readTree()) != null; ) {
            for (Tree t : tree) {
                if (!t.isPreTerminal())
                    continue;
                char type = 'O';
                Tree grandma = t.ancestor(1, tree);
                String grandmaValue = ((CoreLabel) grandma.label()).value();
                // grup.nom.x
                if (nePattern.matcher(grandmaValue).find())
                    type = grandmaValue.charAt(9);
                else // else check the pos for np0000x or not
                {
                    String pos = ((CoreLabel) t.label()).value();
                    if (npPattern.matcher(pos).find())
                        type = pos.charAt(6);
                }
                Tree wordNode = t.firstChild();
                String word = ((CoreLabel) wordNode.label()).value();
                sb.append(word).append("\t");
                switch(type) {
                    case 'p':
                        sb.append("PERS");
                        break;
                    case 'l':
                        sb.append("LUG");
                        break;
                    case 'o':
                        sb.append("ORG");
                        break;
                    case '0':
                        sb.append("OTROS");
                        break;
                    default:
                        sb.append("O");
                }
                sb.append(nl);
            }
            sb.append(nl);
        }
        System.out.print(sb.toString());
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 3 with SpanishTreeReaderFactory

use of edu.stanford.nlp.trees.international.spanish.SpanishTreeReaderFactory in project CoreNLP by stanfordnlp.

the class MultiWordPreprocessor method resolveDummyTags.

private static void resolveDummyTags(File treeFile, TwoDimensionalCounter<String, String> unigramTagger, boolean retainNER, TreeNormalizer tn) {
    TreeFactory tf = new LabeledScoredTreeFactory();
    MultiWordTreeExpander expander = new MultiWordTreeExpander();
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        PrintWriter pw = new PrintWriter(new PrintStream(new FileOutputStream(new File(treeFile + ".fixed")), false, "UTF-8"));
        int nTrees = 0;
        for (Tree t; (t = tr.readTree()) != null; nTrees++) {
            traverseAndFix(t, null, unigramTagger, retainNER);
            // Now "decompress" further the expanded trees formed by
            // multiword token splitting
            t = expander.expandPhrases(t, tn, tf);
            if (tn != null)
                t = tn.normalizeWholeTree(t, tf);
            pw.println(t.toString());
        }
        pw.close();
        tr.close();
        System.out.println("Processed " + nTrees + " trees");
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}