adding transliteration models. #577
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -33,25 +33,36 @@ public class RelationAnnotator extends Annotator { | |
| private ACERelationConstrainedClassifier constrainedClassifier; | ||
| private Gazetteers gazetteers; | ||
| private WordNetManager wordNet; | ||
| private String type = "ACE"; // default relation type | ||
|
|
||
| public RelationAnnotator() { | ||
| this(true); | ||
| } | ||
|
|
||
| public RelationAnnotator(boolean lazilyInitialize) { | ||
| this(lazilyInitialize, "ACE"); | ||
| } | ||
|
|
||
| public RelationAnnotator(boolean lazilyInitialize, String type) { | ||
| super(ViewNames.RELATION, new String[]{ViewNames.MENTION, ViewNames.POS, ViewNames.DEPENDENCY_STANFORD, ViewNames.SHALLOW_PARSE}, lazilyInitialize); | ||
| this.type = (type.contains("ACE")) ? "ACE" : "SEMEVAL"; | ||
| } | ||
|
|
||
| @Override | ||
| public void initialize(ResourceManager rm) { | ||
| try { | ||
| Datastore ds = new Datastore(new ResourceConfigurator().getDefaultConfig()); | ||
| String modelFile; | ||
| String lexFile; | ||
| if (type.equals("ACE")) { | ||
| File modelDir = ds.getDirectory("org.cogcomp.re", "ACE_GOLD_BI", 1.0, false); | ||
| modelFile = modelDir.getPath() + File.separator + "ACE_GOLD_BI" + File.separator + "ACE_GOLD_BI.lc"; | ||
| lexFile = modelDir.getPath() + File.separator + "ACE_GOLD_BI" + File.separator + "ACE_GOLD_BI.lex"; | ||
| } else { | ||
| File modelDir = ds.getDirectory("org.cogcomp.re", "SEMEVAL", 1.1, false); | ||
| modelFile = modelDir.getPath() + File.separator + "SEMEVAL" + File.separator + "SEMEVAL.lc"; | ||
| lexFile = modelDir.getPath() + File.separator + "SEMEVAL" + File.separator + "SEMEVAL.lex"; | ||
| } | ||
|
There was a problem hiding this comment. @Slash0BZ this is ok? I think it's not working .... There was a problem hiding this comment. Did you use the same classifiers or different classifiers? There was a problem hiding this comment. My bad, I forgot it's a different classifier. The classifier for SemEval is |
||
| relationClassifier = new relation_classifier(); | ||
| relationClassifier.readModel(modelFile); | ||
| relationClassifier.readLexicon(lexFile); | ||
|
|
@@ -61,61 +72,64 @@ public void initialize(ResourceManager rm) { | |
| WordNetManager.loadConfigAsClasspathResource(true); | ||
| wordNet = WordNetManager.getInstance(); | ||
| gazetteers = GazetteersFactory.get(); | ||
| } catch (Exception e) { | ||
| e.printStackTrace(); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
| public void addView(TextAnnotation record) throws AnnotatorException { | ||
| if (!isInitialized()) { | ||
| doInitialize(); | ||
| } | ||
| if (!record.hasView(ViewNames.POS)) { | ||
| throw new AnnotatorException("Missing required view POS"); | ||
| } | ||
| if (!record.hasView(ViewNames.DEPENDENCY_STANFORD)) { | ||
| throw new AnnotatorException("Missing required view DEPENDENCY_STANFORD"); | ||
| } | ||
| if (!record.hasView(ViewNames.SHALLOW_PARSE)) { | ||
| throw new AnnotatorException("Missing required view SHALLOW_PARSE"); | ||
| } | ||
| if (!record.hasView(ViewNames.MENTION)) { | ||
| // TODO: show error messages if the mentions are not typed. | ||
|
There was a problem hiding this comment. What you can do here (outside this 'if' of course) is something like else{
if (record.getView(ViewNames.MENTION).getConstituents().get(0).getAttribute("EntityType").equals("MENTION")){
//The model does not have type
}
} |
||
| throw new AnnotatorException("Missing required view MENTION"); | ||
| } | ||
|
|
||
| View mentionView = record.getView(ViewNames.MENTION); | ||
| View annotatedTokenView = new SpanLabelView("RE_ANNOTATED", record); | ||
| for (Constituent co : record.getView(ViewNames.TOKENS).getConstituents()) { | ||
| Constituent c = co.cloneForNewView("RE_ANNOTATED"); | ||
| for (String s : co.getAttributeKeys()) { | ||
| c.addAttribute(s, co.getAttribute(s)); | ||
| } | ||
| c.addAttribute("WORDNETTAG", BIOFeatureExtractor.getWordNetTags(wordNet, c)); | ||
| c.addAttribute("WORDNETHYM", BIOFeatureExtractor.getWordNetHyms(wordNet, c)); | ||
| annotatedTokenView.addConstituent(c); | ||
| } | ||
| record.addView("RE_ANNOTATED", annotatedTokenView); | ||
| for (int i = 0; i < record.getNumberOfSentences(); i++) { | ||
| Sentence curSentence = record.getSentence(i); | ||
| List<Constituent> cins = mentionView.getConstituentsCoveringSpan(curSentence.getStartSpan(), curSentence.getEndSpan()); | ||
| for (int j = 0; j < cins.size(); j++) { | ||
| for (int k = j + 1; k < cins.size(); k++) { | ||
| if (k == j) continue; | ||
| Constituent source = cins.get(j); | ||
| Constituent target = cins.get(k); | ||
| Constituent sourceHead = MentionAnnotator.getHeadConstituent(source, ""); | ||
| Constituent targetHead = MentionAnnotator.getHeadConstituent(target, ""); | ||
| source.addAttribute("GAZ", ((FlatGazetteers) gazetteers).annotatePhrase(sourceHead)); | ||
| target.addAttribute("GAZ", ((FlatGazetteers) gazetteers).annotatePhrase(targetHead)); | ||
| Relation for_test_forward = new Relation("PredictedRE", source, target, 1.0f); | ||
| Relation for_test_backward = new Relation("PredictedRE", target, source, 1.0f); | ||
| String tag_forward = constrainedClassifier.discreteValue(for_test_forward); | ||
| String tag_backward = constrainedClassifier.discreteValue(for_test_backward); | ||
|
|
||
| if (tag_forward.equals(ACEMentionReader.getOppoName(tag_backward)) && !tag_forward.equals("NOT_RELATED")) { | ||
| String tag = tag_forward; | ||
| Constituent first = source; | ||
| Constituent second = target; | ||
| if (tag_forward.length() > tag_backward.length()) { | ||
| tag = tag_backward; | ||
| first = target; | ||
| second = source; | ||
|
|
@@ -127,32 +141,32 @@ public void addView(TextAnnotation record) throws AnnotatorException { | |
| mentionView.addRelation(r); | ||
| } | ||
| if (!tag_forward.equals(ACEMentionReader.getOppoName(tag_backward)) && | ||
| (!tag_forward.equals("NOT_RELATED") || !tag_backward.equals("NOT_RELATED"))) { | ||
| double forward_score = 0.0; | ||
| double backward_score = 0.0; | ||
| ScoreSet scores = relationClassifier.scores(for_test_forward); | ||
| Score[] scoresArray = scores.toArray(); | ||
| for (Score s : scoresArray) { | ||
| if (s.value.equals(tag_forward)) { | ||
| forward_score = s.score; | ||
| } | ||
| } | ||
| scores = relationClassifier.scores(for_test_backward); | ||
| scoresArray = scores.toArray(); | ||
| for (Score s : scoresArray) { | ||
| if (s.value.equals(tag_forward)) { | ||
| backward_score = s.score; | ||
| } | ||
| } | ||
| String tag = tag_forward; | ||
| Constituent first = source; | ||
| Constituent second = target; | ||
| if (forward_score < backward_score && backward_score - forward_score > 0.005) { | ||
| tag = tag_backward; | ||
| first = target; | ||
| second = source; | ||
| } | ||
| if (!tag.equals("NOT_RELATED")) { | ||
| String coarseType = ACERelationTester.getCoarseType(tag); | ||
| Relation r = new Relation(coarseType, first, second, 1.0f); | ||
| r.addAttribute("RelationType", coarseType); | ||
|
|
@@ -163,7 +177,7 @@ public void addView(TextAnnotation record) throws AnnotatorException { | |
| } | ||
| } | ||
| } | ||
| record.addView(ViewNames.RELATION, mentionView); | ||
|
There was a problem hiding this comment. @Slash0BZ how does it look now? There was a problem hiding this comment. here There was a problem hiding this comment. Ah I see. I think it won't make any big problems. Will remember it ... |
||
| } | ||
|
|
||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please add a corresponding switch case in the 'getViewType()' method (https://github.com/danyaljj/illinois-cogcomp-nlp-1/blob/60b45aadcd689fbe5fc6e0af66ca0aa585c0cff7/core-utilities/src/main/java/edu/illinois/cs/cogcomp/core/datastructures/ViewNames.java#L134)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done.