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

Example 21 with TregexPattern

use of edu.stanford.nlp.trees.tregex.TregexPattern 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 22 with TregexPattern

use of edu.stanford.nlp.trees.tregex.TregexPattern 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 23 with TregexPattern

use of edu.stanford.nlp.trees.tregex.TregexPattern 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);
    }
}

Example 24 with TregexPattern

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

the class CoordinationTransformer method MWETransform.

/**
   * Puts all multi-word expressions below a single constituent labeled "MWE".
   * Patterns for multi-word expressions are defined in MWE_PATTERNS.
   */
public static Tree MWETransform(Tree t) {
    for (TregexPattern p : MWE_PATTERNS) {
        Tsurgeon.processPattern(p, MWE_OPERATION, t);
    }
    Tsurgeon.processPattern(ACCORDING_TO_PATTERN, ACCORDING_TO_OPERATION, t);
    Tsurgeon.processPattern(BUT_ALSO_PATTERN, BUT_ALSO_OPERATION, t);
    Tsurgeon.processPattern(AT_RBS_PATTERN, AT_RBS_OPERATION, t);
    Tsurgeon.processPattern(AT_ALL_PATTERN, AT_ALL_OPERATION, t);
    return t;
}

Example 25 with TregexPattern

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

the class GenerateTrees method readGrammar.

public void readGrammar(BufferedReader bin) {
    try {
        String line;
        Section section = Section.TERMINALS;
        while ((line = bin.readLine()) != null) {
            line = line.trim();
            if (line.equals("")) {
                continue;
            }
            if (line.length() > 0 && line.charAt(0) == '#') {
                // skip comments
                continue;
            }
            try {
                Section newSection = Section.valueOf(line.toUpperCase());
                section = newSection;
                if (section == Section.TSURGEON) {
                    // this will tregex pattern until it has eaten a blank
                    // line, then read tsurgeon until it has eaten another
                    // blank line.
                    Pair<TregexPattern, TsurgeonPattern> operation = Tsurgeon.getOperationFromReader(bin, compiler);
                    tsurgeons.add(operation);
                }
                continue;
            } catch (IllegalArgumentException e) {
            // never mind, not an enum
            }
            String[] pieces = line.split(" +");
            switch(section) {
                case TSURGEON:
                    {
                        throw new RuntimeException("Found a non-empty line in a tsurgeon section after reading the operation");
                    }
                case TERMINALS:
                    {
                        Counter<String> productions = terminals.get(pieces[0]);
                        if (productions == null) {
                            productions = new ClassicCounter<>();
                            terminals.put(pieces[0], productions);
                        }
                        for (int i = 1; i < pieces.length; ++i) {
                            productions.incrementCount(pieces[i]);
                        }
                        break;
                    }
                case NONTERMINALS:
                    {
                        Counter<List<String>> productions = nonTerminals.get(pieces[0]);
                        if (productions == null) {
                            productions = new ClassicCounter<>();
                            nonTerminals.put(pieces[0], productions);
                        }
                        String[] sublist = Arrays.copyOfRange(pieces, 1, pieces.length);
                        productions.incrementCount(Arrays.asList(sublist));
                    }
            }
        }
    } catch (IOException e) {
        throw new RuntimeIOException(e);
    }
}