Examples of edu.stanford.nlp.trees.GrammaticalRelation

edu.stanford.nlp.trees.GrammaticalRelation
{@code GrammaticalRelation} is used to define astandardized, hierarchical set of grammatical relations, together with patterns for identifying them in parse trees.
Each GrammaticalRelation has:
- A String short name, which should be a lowercase abbreviation of some kind (in the fure mainly Universal Dependency names).
- A String long name, which should be descriptive.
- A parent in the GrammaticalRelation hierarchy.
- A {@link Pattern Pattern} calledsourcePattern which matches (parent) nodes from which this GrammaticalRelation could hold. (Note: this is done with the Java regex Pattern matches() predicate. The pattern must match the whole node name, and ^ or $ aren't needed. Tregex constructions like __ do not work. Use ".*" to be applicable at all nodes. This prefiltering is used for efficiency.)
- A list of zero or more {@link TregexPattern TregexPatterns} called targetPatterns,which describe the local tree structure which must hold between the source node and a target node for the GrammaticalRelation to apply. (Note: {@code tregex}regular expressions match with the {@code find()} method, whileliteral string label descriptions that are not regular expressions must be {@code equals()}.)
The targetPatterns associated with a GrammaticalRelation are designed as follows. In order to recognize a grammatical relation X holding between nodes A and B in a parse tree, we want to associate with GrammaticalRelation X a {@link TregexPattern TregexPattern} such that:
- the root of the pattern matches A, and
- the pattern includes a node labeled "target", which matches B.
For example, for the grammatical relation PREDICATE which holds between a clause and its primary verb phrase, we might want to use the pattern {@code "S < VP=target"}, in which the root will match a clause and the node labeled "target" will match the verb phrase.
For a given grammatical relation, the method {@link GrammaticalRelation#getRelatedNodes getRelatedNodes()}takes a Tree node as an argument and attempts to return other nodes which have this grammatical relation to the argument node. By default, this method operates as follows: it steps through the patterns in the pattern list, trying to match each pattern against the argument node, until it finds some matches. If a pattern matches, all matching nodes (that is, each node which corresponds to node label "target" in some match) are returned as a list; otherwise the next pattern is tried.
For some grammatical relations, we need more sophisticated logic to identify related nodes. In such cases, {@link GrammaticalRelation#getRelatedNodes getRelatedNodes()}can be overridden on a per-relation basis using anonymous subclassing.
@see GrammaticalStructure @see EnglishGrammaticalStructure @see EnglishGrammaticalRelations @see edu.stanford.nlp.trees.international.pennchinese.ChineseGrammaticalRelations @author Bill MacCartney @author Galen Andrew (refactoring English-specific stuff) @author Ilya Sherman (refactoring annotation-relation pairing, which is now gone)

      // search for the complement: pobj|pcomp(mwp1,X)
      for (TypedDependency td2 : list) {
        if (td2.gov().equals(mwp1) && td2.reln() == PREPOSITIONAL_OBJECT) {
          pobj = td2;
          // create the new gr relation
          GrammaticalRelation gr = EnglishGrammaticalRelations.getPrep(mwp[0] + '_' + mwp[1]);
          newTypedDeps.add(new TypedDependency(gr, governor, pobj.dep()));
        }
        if (td2.gov().equals(mwp1) && td2.reln() == PREPOSITIONAL_COMPLEMENT) {
          pobj = td2;
          // create the new gr relation
          GrammaticalRelation gr = EnglishGrammaticalRelations.getPrepC(mwp[0] + '_' + mwp[1]);
          newTypedDeps.add(new TypedDependency(gr, governor, pobj.dep()));
        }
      }


      if (pobj == null) {

View Full Code Here

          if (edge+n > edgePath.size())
            break;
          StringBuilder sbRelsHi = new StringBuilder();
          StringBuilder sbRelsLo = new StringBuilder();
          for (int elt = edge; elt < edge+n; elt++) {
            GrammaticalRelation gr = edgePath.get(elt).getRelation();
            sbRelsHi.append(generalizeRelation(gr));
            sbRelsHi.append("_");
            sbRelsLo.append(gr);
            sbRelsLo.append("_");
          }

View Full Code Here

  public static List<String> dependencyPathAsList(List<SemanticGraphEdge> edgePath, IndexedWord node, boolean generalize) {
    if(edgePath == null) return null;
    List<String> path = new ArrayList<String>();
    for (SemanticGraphEdge edge : edgePath) {
      IndexedWord nextNode;
      GrammaticalRelation relation;
      if (generalize) {
        relation = generalizeRelation(edge.getRelation());
      } else {
        relation = edge.getRelation();
      }

View Full Code Here

    SemanticGraph ccProcessed = document.get(CoreAnnotations.SentencesAnnotation.class).get(0)
                                        .get(
                                            SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class);
    Collection<TypedDependency> dependencies = ccProcessed.typedDependencies();


    GrammaticalRelation expected = EnglishGrammaticalRelations.getConj("and");
    assertThat(dependencies.stream().map(d -> d.reln()).collect(toList()),
        hasItem(expected));
  }

View Full Code Here


    if(dependency.getRoots().isEmpty()) return null;
    // root relation
    if(dependency.getFirstRoot().equals(headIndexedWord)) return "root";
    if(!dependency.containsVertex(dependency.getParent(headIndexedWord))) return null;
    GrammaticalRelation relation = dependency.reln(dependency.getParent(headIndexedWord), headIndexedWord);


    // adjunct relations
    if(relation.toString().startsWith("prep") || relation == EnglishGrammaticalRelations.PREPOSITIONAL_OBJECT || relation == EnglishGrammaticalRelations.TEMPORAL_MODIFIER || relation == EnglishGrammaticalRelations.ADV_CLAUSE_MODIFIER || relation == EnglishGrammaticalRelations.ADVERBIAL_MODIFIER || relation == EnglishGrammaticalRelations.PREPOSITIONAL_COMPLEMENT) return "adjunct";


    // subject relations
    if(relation == EnglishGrammaticalRelations.NOMINAL_SUBJECT || relation == EnglishGrammaticalRelations.CLAUSAL_SUBJECT) return "subject";
    if(relation == EnglishGrammaticalRelations.NOMINAL_PASSIVE_SUBJECT || relation == EnglishGrammaticalRelations.CLAUSAL_PASSIVE_SUBJECT) return "subject";

View Full Code Here

    if(headIndexedWord == null) return 0;


    int count = 0;
    List<Pair<GrammaticalRelation, IndexedWord>> childPairs = dependency.childPairs(headIndexedWord);
    for(Pair<GrammaticalRelation, IndexedWord> childPair : childPairs) {
      GrammaticalRelation gr = childPair.first;
      IndexedWord word = childPair.second;
      if(gr == EnglishGrammaticalRelations.ADJECTIVAL_MODIFIER || gr == EnglishGrammaticalRelations.VERBAL_MODIFIER ||
         gr == EnglishGrammaticalRelations.RELATIVE_CLAUSE_MODIFIER || gr.toString().startsWith("prep_")) {
        count++;
      }
      // add noun modifier when the mention isn't a NER
      if(nerString.equals("O") && gr == EnglishGrammaticalRelations.NOUN_COMPOUND_MODIFIER) {
        count++;

View Full Code Here

    }
    // check the parent
    List<Pair<GrammaticalRelation,IndexedWord>> parentPairs = dependency.parentPairs(headIndexedWord);
    if (!parentPairs.isEmpty()) {
      Pair<GrammaticalRelation,IndexedWord> parentPair = parentPairs.get(0);
      GrammaticalRelation gr = parentPair.first;
      // check negative prepositions
      if(dict.neg_relations.contains(gr.toString())) return 1;
    }
    return 0;
  }

View Full Code Here

   *
   * @param conjunctionString The conjunction to make a GrammaticalRelation out of
   * @return A grammatical relation for this conjunction
   */
  public static GrammaticalRelation getConj(String conjunctionString) {
    GrammaticalRelation result = conjs.get(conjunctionString);
    if (result == null) {
      result = new GrammaticalRelation(Language.English, "conj", "conj_collapsed", null, DEPENDENT, conjunctionString);
      conjs.put(conjunctionString, result);
      threadSafeAddRelation(result);
    }
    return result;
  }

View Full Code Here

   *
   * @param prepositionString The presposition to make a GrammaticalRelation out of
   * @return A grammatical relation for this presposition
   */
  public static GrammaticalRelation getPrep(String prepositionString) {
    GrammaticalRelation result = preps.get(prepositionString);
    if (result == null) {
      result = new GrammaticalRelation(Language.English, "prep", "prep_collapsed", null, DEPENDENT, prepositionString);
      preps.put(prepositionString, result);
      threadSafeAddRelation(result);
    }
    return result;
  }

View Full Code Here

   *
   * @param prepositionString The presposition to make a GrammaticalRelation out of
   * @return A grammatical relation for this presposition
   */
  public static GrammaticalRelation getPrepC(String prepositionString) {
    GrammaticalRelation result = prepsC.get(prepositionString);
    if (result == null) {
      result = new GrammaticalRelation(Language.English, "prepc", "prepc_collapsed", null, DEPENDENT, prepositionString);
      prepsC.put(prepositionString, result);
      threadSafeAddRelation(result);
    }
    return result;
  }

View Full Code Here

0 1 2

TOP

Related Classes of edu.stanford.nlp.trees.GrammaticalRelation

edu.stanford.nlp.dcoref.Mention

edu.stanford.nlp.ie.machinereading.BasicRelationFeatureFactory

edu.stanford.nlp.parser.nndep.DependencyParser

edu.stanford.nlp.parser.nndep.DependencyParserITest

edu.stanford.nlp.pipeline.AnnotationSerializer$IntermediateSemanticGraph

edu.stanford.nlp.pipeline.ProtobufAnnotationSerializer

edu.stanford.nlp.semgraph.SemanticGraphUtils

edu.stanford.nlp.semgraph.semgrex.ssurgeon.AddDep

edu.stanford.nlp.semgraph.semgrex.ssurgeon.AddEdge

edu.stanford.nlp.trees.EnglishGrammaticalRelations

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.