When I run JIGG using the annotators corenlp[tokenize,ssplit],berkeleyparser,corenlp[lemma,ner,dcoref], the following error is happened (regardless of the length of the sentence):
...
[main] WARN edu.stanford.nlp.ie.NumberNormalizer - java.lang.NumberFormatException: Bad number put into wordToNumber. Word is: "pm", originally part of "pm o", piece # 0
edu.stanford.nlp.ie.NumberNormalizer.wordToNumber(NumberNormalizer.java:381)
edu.stanford.nlp.ie.NumberNormalizer.findNumbers(NumberNormalizer.java:721)
edu.stanford.nlp.ie.NumberNormalizer.findAndMergeNumbers(NumberNormalizer.java:810)
edu.stanford.nlp.time.TimeExpressionExtractorImpl.extractTimeExpressions(TimeExpressionExtractorImpl.java:190)
edu.stanford.nlp.time.TimeExpressionExtractorImpl.extractTimeExpressions(TimeExpressionExtractorImpl.java:184)
edu.stanford.nlp.time.TimeExpressionExtractorImpl.extractTimeExpressionCoreMaps(TimeExpressionExtractorImpl.java:115)
edu.stanford.nlp.time.TimeExpressionExtractorImpl.extractTimeExpressionCoreMaps(TimeExpressionExtractorImpl.java:105)
edu.stanford.nlp.ie.regexp.NumberSequenceClassifier.runSUTime(NumberSequenceClassifier.java:345)
edu.stanford.nlp.ie.regexp.NumberSequenceClassifier.classifyWithSUTime(NumberSequenceClassifier.java:143)
edu.stanford.nlp.ie.regexp.NumberSequenceClassifier.classifyWithGlobalInformation(NumberSequenceClassifier.java:106)
edu.stanford.nlp.ie.NERClassifierCombiner.recognizeNumberSequences(NERClassifierCombiner.java:368)
edu.stanford.nlp.ie.NERClassifierCombiner.classifyWithGlobalInformation(NERClassifierCombiner.java:311)
edu.stanford.nlp.ie.AbstractSequenceClassifier.classifySentenceWithGlobalInformation(AbstractSequenceClassifier.java:343)
edu.stanford.nlp.pipeline.NERCombinerAnnotator.doOneSentence(NERCombinerAnnotator.java:290)
edu.stanford.nlp.pipeline.SentenceAnnotator.annotate(SentenceAnnotator.java:102)
edu.stanford.nlp.pipeline.NERCombinerAnnotator.annotate(NERCombinerAnnotator.java:253)
edu.stanford.nlp.pipeline.AnnotationPipeline.annotate(AnnotationPipeline.java:76)
edu.stanford.nlp.pipeline.StanfordCoreNLP.annotate(StanfordCoreNLP.java:660)
...
Exception in thread "main" java.lang.NullPointerException
at edu.stanford.nlp.coref.md.DependencyCorefMentionFinder.extractNPorPRPFromDependency(DependencyCorefMentionFinder.java:104)
at edu.stanford.nlp.coref.md.DependencyCorefMentionFinder.findMentions(DependencyCorefMentionFinder.java:63)
at edu.stanford.nlp.pipeline.CorefMentionAnnotator.annotate(CorefMentionAnnotator.java:154)
at edu.stanford.nlp.pipeline.DeterministicCorefAnnotator.annotate
...
There are two types in this error: (1) [main] WARN edu.stanford.nlp.ie.NumberNormalizer and (2) Exception in thread "main" java.lang.NullPointerException. I confirmed that the error (1) happens when using the annotators ner. The error (2) does not happen when using the ner, but it happens when using the dcoref.
When I run JIGG using the annotators
corenlp[tokenize,ssplit],berkeleyparser,corenlp[lemma,ner,dcoref]
, the following error is happened (regardless of the length of the sentence):There are two types in this error: (1) [main] WARN edu.stanford.nlp.ie.NumberNormalizer and (2) Exception in thread "main" java.lang.NullPointerException. I confirmed that the error (1) happens when using the annotators
ner
. The error (2) does not happen when using thener
, but it happens when using thedcoref
.