Examples with TregexMatcher edu.stanford.nlp.trees.tregex.TregexMatcher used on opensource projects

Example 16 with TregexMatcher

use of edu.stanford.nlp.trees.tregex.TregexMatcher in project CoreNLP by stanfordnlp.

the class MWEPreprocessor method countMWEStatistics.

public static void countMWEStatistics(Tree t, TwoDimensionalCounter<String, String> unigramTagger, TwoDimensionalCounter<String, String> labelPreterm, TwoDimensionalCounter<String, String> pretermLabel, TwoDimensionalCounter<String, String> labelTerm, TwoDimensionalCounter<String, String> termLabel) {
    updateTagger(unigramTagger, t);
    //Count MWE statistics
    TregexMatcher m = pMWE.matcher(t);
    while (m.findNextMatchingNode()) {
        Tree match = m.getMatch();
        String label = match.value();
        if (RESOLVE_DUMMY_TAGS && label.equals(FrenchXMLTreeReader.MISSING_PHRASAL))
            continue;
        String preterm = SentenceUtils.listToString(match.preTerminalYield());
        String term = SentenceUtils.listToString(match.yield());
        labelPreterm.incrementCount(label, preterm);
        pretermLabel.incrementCount(preterm, label);
        labelTerm.incrementCount(label, term);
        termLabel.incrementCount(term, label);
    }
}

Example 17 with TregexMatcher

use of edu.stanford.nlp.trees.tregex.TregexMatcher in project CoreNLP by stanfordnlp.

the class RHSFrequency method main.

public static void main(String[] args) {
    if (args.length < minArgs) {
        System.out.println(usage.toString());
        System.exit(-1);
    }
    TreebankLangParserParams tlpp = new EnglishTreebankParserParams();
    DiskTreebank tb = null;
    String encoding = "UTF-8";
    TregexPattern rootMatch = null;
    for (int i = 0; i < args.length; i++) {
        if (args[i].startsWith("-")) {
            switch(args[i]) {
                case "-l":
                    Language lang = Language.valueOf(args[++i].trim());
                    tlpp = lang.params;
                    break;
                case "-e":
                    encoding = args[++i];
                    break;
                default:
                    System.out.println(usage.toString());
                    System.exit(-1);
            }
        } else {
            rootMatch = TregexPattern.compile("@" + args[i++]);
            if (tb == null) {
                if (tlpp == null) {
                    System.out.println(usage.toString());
                    System.exit(-1);
                } else {
                    tlpp.setInputEncoding(encoding);
                    tlpp.setOutputEncoding(encoding);
                    tb = tlpp.diskTreebank();
                }
            }
            tb.loadPath(args[i++]);
        }
    }
    Counter<String> rhsCounter = new ClassicCounter<>();
    for (Tree t : tb) {
        TregexMatcher m = rootMatch.matcher(t);
        while (m.findNextMatchingNode()) {
            Tree match = m.getMatch();
            StringBuilder sb = new StringBuilder();
            for (Tree kid : match.children()) sb.append(kid.value()).append(" ");
            rhsCounter.incrementCount(sb.toString().trim());
        }
    }
    List<String> biggestKeys = new ArrayList<>(rhsCounter.keySet());
    Collections.sort(biggestKeys, Counters.toComparatorDescending(rhsCounter));
    PrintWriter pw = tlpp.pw();
    for (String rhs : biggestKeys) pw.printf("%s\t%d%n", rhs, (int) rhsCounter.getCount(rhs));
    pw.close();
}

Example 18 with TregexMatcher

use of edu.stanford.nlp.trees.tregex.TregexMatcher in project CoreNLP by stanfordnlp.

the class RuleBasedCorefMentionFinder method extractNPorPRP.

protected static void extractNPorPRP(CoreMap s, List<Mention> mentions, Set<IntPair> mentionSpanSet, Set<IntPair> namedEntitySpanSet) {
    List<CoreLabel> sent = s.get(CoreAnnotations.TokensAnnotation.class);
    Tree tree = s.get(TreeCoreAnnotations.TreeAnnotation.class);
    tree.indexLeaves();
    SemanticGraph dependency = s.get(SemanticGraphCoreAnnotations.EnhancedDependenciesAnnotation.class);
    TregexPattern tgrepPattern = npOrPrpMentionPattern;
    TregexMatcher matcher = tgrepPattern.matcher(tree);
    while (matcher.find()) {
        Tree t = matcher.getMatch();
        List<Tree> mLeaves = t.getLeaves();
        int beginIdx = ((CoreLabel) mLeaves.get(0).label()).get(CoreAnnotations.IndexAnnotation.class) - 1;
        int endIdx = ((CoreLabel) mLeaves.get(mLeaves.size() - 1).label()).get(CoreAnnotations.IndexAnnotation.class);
        // try not to have span that ends with ,
        if (",".equals(sent.get(endIdx - 1).word())) {
            endIdx--;
        }
        IntPair mSpan = new IntPair(beginIdx, endIdx);
        if (!mentionSpanSet.contains(mSpan) && !insideNE(mSpan, namedEntitySpanSet)) {
            int dummyMentionId = -1;
            Mention m = new Mention(dummyMentionId, beginIdx, endIdx, dependency, new ArrayList<>(sent.subList(beginIdx, endIdx)), t);
            mentions.add(m);
            mentionSpanSet.add(mSpan);
        }
    }
}

Example 19 with TregexMatcher

use of edu.stanford.nlp.trees.tregex.TregexMatcher in project CoreNLP by stanfordnlp.

the class TregexPoweredTreebankParserParams method getAnnotationString.

/**
   * Build a string of annotations for the given tree.
   *
   * @param t The input tree (with non-language specific annotation
   *          already done, so you need to strip back to basic categories)
   * @param root The root of the current tree (can be null for words)
   * @return A (possibly empty) string of annotations to add to the
   *         given tree
   */
protected String getAnnotationString(Tree t, Tree root) {
    // Accumulate all annotations in this string
    StringBuilder annotationStr = new StringBuilder();
    for (String featureName : features) {
        Pair<TregexPattern, Function<TregexMatcher, String>> behavior = annotationPatterns.get(featureName);
        TregexMatcher m = behavior.first().matcher(root);
        if (m.matchesAt(t))
            annotationStr.append(behavior.second().apply(m));
    }
    return annotationStr.toString();
}

Example 20 with TregexMatcher

use of edu.stanford.nlp.trees.tregex.TregexMatcher in project CoreNLP by stanfordnlp.

the class TregexPoweredTreebankParserParams method compileAnnotations.

/**
   * Compile the {@link #annotations} collection given a
   * particular head finder. Subclasses should call this method at
   * least once before the class is used, and whenever the head finder
   * is changed.
   */
protected void compileAnnotations(HeadFinder hf) {
    TregexPatternCompiler compiler = new TregexPatternCompiler(hf);
    annotationPatterns.clear();
    for (Map.Entry<String, Pair<String, Function<TregexMatcher, String>>> annotation : annotations.entrySet()) {
        TregexPattern compiled;
        try {
            compiled = compiler.compile(annotation.getValue().first());
        } catch (TregexParseException e) {
            int nth = annotationPatterns.size() + 1;
            log.info("Parse exception on annotation pattern #" + nth + " initialization: " + e);
            continue;
        }
        Pair<TregexPattern, Function<TregexMatcher, String>> behavior = new Pair<>(compiled, annotation.getValue().second());
        annotationPatterns.put(annotation.getKey(), behavior);
    }
}