101471-3.txt

In addition to The Black Hermit and Wizard of the Crow, this author is better known for a novel in which Mugo betrays the revolutionary Kihika, as well as another in which Munira burns down Wanjas brothel.

Wikifier Error

Annotating the data with gazetteers
Annotating the data with context-aggregation features (if necessary)
Done Annotating the data with expressive features...
Annontating data with the models tagger, the inference algoritm is: GREEDY
Extracting features for level 2 inference
Done - Extracting features for level 2 inference
Done Annontating data with the models tagger, the inference algoritm is: GREEDY
Inference time: 32 milliseconds
Constructing a problem for the following text:
For 10 points, name this author of Sketches by Boz, who wrote about a clock-stopping jilted spinster who mindfucks Estelle and Pip in Great Expectations.

Annotating mention view..
2 milliseconds elapsed on constructing the TF-IDF representation of the input text...101469-4.txt
Getting the wikifiable mentions candidates
Getting the Wikifiable entitites
Getting the text annotation
Adding NER candidates for 101469-4.txt
Adding SHALLOW_PARSE and subChunk candidates for 101469-4.txt
Done - Getting the text annotation
Adding manually specified mentions
Regex matching...
Matched regex entity Estelle and Pip in Great Expectations[115-152]{21-27}
Matched regex entity Pip in Great Expectations[127-152]{23-27}
Matched regex entity Great Expectations[134-152]{25-27}
Finished adding regex large chunk matching
Extracting the candidate disambiguations for the mentions
Done constructing the Wikifiable entities
     ----  almost there....
107 milliseconds elapsed on constructing potentially wikifiable entitites in the input text...101469-4.txt
Done constructing the problem; running the inference
Inference on the document  -- 101469-4.txt
1 milliseconds elapsed extracting features for the level: FeatureExtractorTitlesMatch
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorTitlesMatch
10 milliseconds elapsed extracting features for the level: FeatureExtractorLexical
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorLexical
3 milliseconds elapsed extracting features for the level: FeatureExtractorCoherence
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorCoherence
Relational inference took 0ms
Discarded 0 hypothesis
Annotation at test time--76 milliseconds elapsed to annotate the document 101469-4.txt
Done  running the inference
Saving the simplest-form no nested entities Wikification output in html format
Saving the full annotation in XML
Saving the NER output
Processing the file : data/input/101471-0.txt
Constructing the problem...
Annotating the data with expressive features...
Brown clusters OOV statistics:
Data statistics:
		- Total tokens with repetitions =21
		- Total unique tokens  =20
		- Total unique tokens ignore case =20
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt(covers 1288301 unique tokens)
		- Total OOV tokens, Case Sensitive =1
		- OOV tokens, no repetitions, Case Sensitive =1
		- Total OOV tokens even after lowercasing  =1
		- OOV tokens even after lowercasing, no repetition  =1
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brownBllipClusters(covers 95262 unique tokens)
		- Total OOV tokens, Case Sensitive =3
		- OOV tokens, no repetitions, Case Sensitive =3
		- Total OOV tokens even after lowercasing  =3
		- OOV tokens even after lowercasing, no repetition  =3
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/rcv1.clean.tokenized-c1000-p1.paths.txt(covers 85963 unique tokens)
		- Total OOV tokens, Case Sensitive =3
		- OOV tokens, no repetitions, Case Sensitive =3
		- Total OOV tokens even after lowercasing  =3
		- OOV tokens even after lowercasing, no repetition  =3
Annotating the data with gazetteers
Annotating the data with context-aggregation features (if necessary)
Done Annotating the data with expressive features...
Annontating data with the models tagger, the inference algoritm is: GREEDY
Extracting features for level 2 inference
Done - Extracting features for level 2 inference
Done Annontating data with the models tagger, the inference algoritm is: GREEDY
Inference time: 41 milliseconds
Constructing a problem for the following text:
In one of this author's novels, Cheges son loves the preacher Joshuas daughter and abandons the Kameno community.

Annotating mention view..
0 milliseconds elapsed on constructing the TF-IDF representation of the input text...101471-0.txt
Getting the wikifiable mentions candidates
Getting the Wikifiable entitites
Getting the text annotation
Adding NER candidates for 101471-0.txt
Adding SHALLOW_PARSE and subChunk candidates for 101471-0.txt
Done - Getting the text annotation
Adding manually specified mentions
Regex matching...
Finished adding regex large chunk matching
Extracting the candidate disambiguations for the mentions
Done constructing the Wikifiable entities
     ----  almost there....
54 milliseconds elapsed on constructing potentially wikifiable entitites in the input text...101471-0.txt
Done constructing the problem; running the inference
Inference on the document  -- 101471-0.txt
0 milliseconds elapsed extracting features for the level: FeatureExtractorTitlesMatch
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorTitlesMatch
7 milliseconds elapsed extracting features for the level: FeatureExtractorLexical
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorLexical
1 milliseconds elapsed extracting features for the level: FeatureExtractorCoherence
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorCoherence
Could not find WikiMatchData for title Kameno
Relational inference took 0ms
Discarded 0 hypothesis
Annotation at test time--67 milliseconds elapsed to annotate the document 101471-0.txt
Done  running the inference
Saving the simplest-form no nested entities Wikification output in html format
Saving the full annotation in XML
Saving the NER output
Processing the file : data/input/101471-1.txt
Constructing the problem...
Annotating the data with expressive features...
Brown clusters OOV statistics:
Data statistics:
		- Total tokens with repetitions =35
		- Total unique tokens  =29
		- Total unique tokens ignore case =29
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt(covers 1288301 unique tokens)
		- Total OOV tokens, Case Sensitive =3
		- OOV tokens, no repetitions, Case Sensitive =3
		- Total OOV tokens even after lowercasing  =3
		- OOV tokens even after lowercasing, no repetition  =3
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brownBllipClusters(covers 95262 unique tokens)
		- Total OOV tokens, Case Sensitive =4
		- OOV tokens, no repetitions, Case Sensitive =4
		- Total OOV tokens even after lowercasing  =4
		- OOV tokens even after lowercasing, no repetition  =4
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/rcv1.clean.tokenized-c1000-p1.paths.txt(covers 85963 unique tokens)
		- Total OOV tokens, Case Sensitive =3
		- OOV tokens, no repetitions, Case Sensitive =3
		- Total OOV tokens even after lowercasing  =3
		- OOV tokens even after lowercasing, no repetition  =3
Annotating the data with gazetteers
Annotating the data with context-aggregation features (if necessary)
Done Annotating the data with expressive features...
Annontating data with the models tagger, the inference algoritm is: GREEDY
Extracting features for level 2 inference
Done - Extracting features for level 2 inference
Done Annontating data with the models tagger, the inference algoritm is: GREEDY
Inference time: 61 milliseconds
Annotating mention view..
Constructing a problem for the following text:
Thoni commits suicide thanks to rejection by her husband Remi, the title character, in one of this authors plays, while in another, Gathonis pregnancy prevents her marriage to John Muhuuni.

0 milliseconds elapsed on constructing the TF-IDF representation of the input text...101471-1.txt
Getting the wikifiable mentions candidates
Getting the Wikifiable entitites
Getting the text annotation
Adding NER candidates for 101471-1.txt
Adding SHALLOW_PARSE and subChunk candidates for 101471-1.txt
Done - Getting the text annotation
Adding manually specified mentions
Regex matching...
Finished adding regex large chunk matching
Extracting the candidate disambiguations for the mentions
Done constructing the Wikifiable entities
     ----  almost there....
66 milliseconds elapsed on constructing potentially wikifiable entitites in the input text...101471-1.txt
Done constructing the problem; running the inference
Inference on the document  -- 101471-1.txt
0 milliseconds elapsed extracting features for the level: FeatureExtractorTitlesMatch
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorTitlesMatch
21 milliseconds elapsed extracting features for the level: FeatureExtractorLexical
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorLexical
2 milliseconds elapsed extracting features for the level: FeatureExtractorCoherence
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorCoherence
Could not find WikiMatchData for title Reiner_Thoni
[DEBUG][edu.illinois.cs.cogcomp.wikifier.inference.relation.NominalMentionAnalysis] - NOMCOREF DETECTED:Remi[57-61]{9-10} === the title character
[DEBUG][edu.illinois.cs.cogcomp.wikifier.inference.relation.NominalMentionAnalysis] - Force linking Remi[57-61]{9-10} to null
Relational inference took 0ms
Discarded 0 hypothesis
Annotation at test time--117 milliseconds elapsed to annotate the document 101471-1.txt
Done  running the inference
Saving the simplest-form no nested entities Wikification output in html format
Saving the full annotation in XML
Saving the NER output
Processing the file : data/input/101471-2.txt
Constructing the problem...
Annotating the data with expressive features...
Brown clusters OOV statistics:
Data statistics:
		- Total tokens with repetitions =23
		- Total unique tokens  =21
		- Total unique tokens ignore case =21
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt(covers 1288301 unique tokens)
		- Total OOV tokens, Case Sensitive =2
		- OOV tokens, no repetitions, Case Sensitive =2
		- Total OOV tokens even after lowercasing  =2
		- OOV tokens even after lowercasing, no repetition  =2
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brownBllipClusters(covers 95262 unique tokens)
		- Total OOV tokens, Case Sensitive =3
		- OOV tokens, no repetitions, Case Sensitive =3
		- Total OOV tokens even after lowercasing  =3
		- OOV tokens even after lowercasing, no repetition  =3
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/rcv1.clean.tokenized-c1000-p1.paths.txt(covers 85963 unique tokens)
		- Total OOV tokens, Case Sensitive =4
		- OOV tokens, no repetitions, Case Sensitive =4
		- Total OOV tokens even after lowercasing  =4
		- OOV tokens even after lowercasing, no repetition  =4
Annotating the data with gazetteers
Annotating the data with context-aggregation features (if necessary)
Done Annotating the data with expressive features...
Annontating data with the models tagger, the inference algoritm is: GREEDY
Extracting features for level 2 inference
Done - Extracting features for level 2 inference
Done Annontating data with the models tagger, the inference algoritm is: GREEDY
Inference time: 33 milliseconds
Annotating mention view..
Constructing a problem for the following text:
Another of his novels is set in the Republic of Aburiria, where Kamiti and Nyawira pretend to be the title sorcerer.

1 milliseconds elapsed on constructing the TF-IDF representation of the input text...101471-2.txt
Getting the wikifiable mentions candidates
Getting the Wikifiable entitites
Getting the text annotation
Adding NER candidates for 101471-2.txt
Adding SHALLOW_PARSE and subChunk candidates for 101471-2.txt
Done - Getting the text annotation
Adding manually specified mentions
Regex matching...
Matched regex entity Republic of Aburiria[36-56]{8-11}
Matched regex entity Kamiti and Nyawira[64-82]{13-16}
Finished adding regex large chunk matching
Extracting the candidate disambiguations for the mentions
Done constructing the Wikifiable entities
     ----  almost there....
38 milliseconds elapsed on constructing potentially wikifiable entitites in the input text...101471-2.txt
Done constructing the problem; running the inference
Inference on the document  -- 101471-2.txt
0 milliseconds elapsed extracting features for the level: FeatureExtractorTitlesMatch
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorTitlesMatch
9 milliseconds elapsed extracting features for the level: FeatureExtractorLexical
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorLexical
1 milliseconds elapsed extracting features for the level: FeatureExtractorCoherence
0 milliseconds elapsed ranking the candidates at level...FeatureExtractorCoherence
Relational inference took 0ms
Discarded 0 hypothesis
Annotation at test time--93 milliseconds elapsed to annotate the document 101471-2.txt
Done  running the inference
Saving the simplest-form no nested entities Wikification output in html format
Saving the full annotation in XML
Saving the NER output
Processing the file : data/input/101471-3.txt
Constructing the problem...
Annotating the data with expressive features...
Brown clusters OOV statistics:
Data statistics:
		- Total tokens with repetitions =40
		- Total unique tokens  =35
		- Total unique tokens ignore case =33
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt(covers 1288301 unique tokens)
		- Total OOV tokens, Case Sensitive =2
		- OOV tokens, no repetitions, Case Sensitive =2
		- Total OOV tokens even after lowercasing  =2
		- OOV tokens even after lowercasing, no repetition  =2
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/brownBllipClusters(covers 95262 unique tokens)
		- Total OOV tokens, Case Sensitive =5
		- OOV tokens, no repetitions, Case Sensitive =5
		- Total OOV tokens even after lowercasing  =5
		- OOV tokens even after lowercasing, no repetition  =5
	* OOV statistics for the resource: data/NER_Data//BrownHierarchicalWordClusters/rcv1.clean.tokenized-c1000-p1.paths.txt(covers 85963 unique tokens)
		- Total OOV tokens, Case Sensitive =5
		- OOV tokens, no repetitions, Case Sensitive =5
		- Total OOV tokens even after lowercasing  =5
		- OOV tokens even after lowercasing, no repetition  =5
Annotating the data with gazetteers
Annotating the data with context-aggregation features (if necessary)
Done Annotating the data with expressive features...
Annontating data with the models tagger, the inference algoritm is: GREEDY
Extracting features for level 2 inference
Done - Extracting features for level 2 inference
Done Annontating data with the models tagger, the inference algoritm is: GREEDY
Inference time: 52 milliseconds
Annotating mention view..
Constructing a problem for the following text:
In addition to The Black Hermit and Wizard of the Crow, this author is better known for a novel in which Mugo betrays the revolutionary Kihika, as well as another in which Munira burns down Wanjas ...
0 milliseconds elapsed on constructing the TF-IDF representation of the input text...101471-3.txt
Getting the wikifiable mentions candidates
Getting the Wikifiable entitites
Getting the text annotation
Adding NER candidates for 101471-3.txt
Adding SHALLOW_PARSE and subChunk candidates for 101471-3.txt
Done - Getting the text annotation
Adding manually specified mentions
Regex matching...
Matched regex entity The Black Hermit and Wizard of the Crow[15-54]{3-11}
Matched regex entity Black Hermit and Wizard of the Crow[19-54]{4-11}
Matched regex entity Wizard of the Crow[36-54]{7-11}
Finished adding regex large chunk matching
Extracting the candidate disambiguations for the mentions
Done constructing the Wikifiable entities
     ----  almost there....
94 milliseconds elapsed on constructing potentially wikifiable entitites in the input text...101471-3.txt
Done constructing the problem; running the inference
Inference on the document  -- 101471-3.txt
0 milliseconds elapsed extracting features for the level: FeatureExtractorTitlesMatch
1 milliseconds elapsed ranking the candidates at level...FeatureExtractorTitlesMatch
53 milliseconds elapsed extracting features for the level: FeatureExtractorLexical
2 milliseconds elapsed ranking the candidates at level...FeatureExtractorLexical
8 milliseconds elapsed extracting features for the level: FeatureExtractorCoherence
4 milliseconds elapsed ranking the candidates at level...FeatureExtractorCoherence
Could not find WikiMatchData for title The_Black_Hermit
Exception in thread "main" java.lang.NullPointerException
	at edu.illinois.cs.cogcomp.wikifier.models.Mention.getCorefRelationsTo(Mention.java:938)
	at edu.illinois.cs.cogcomp.wikifier.inference.relation.NPAnalysis.forceLinkPERNameChunks(NPAnalysis.java:55)
	at edu.illinois.cs.cogcomp.wikifier.inference.relation.NPAnalysis.infer(NPAnalysis.java:31)
	at edu.illinois.cs.cogcomp.wikifier.models.LinkingProblem.resolveCoherenceRelations(LinkingProblem.java:329)
	at edu.illinois.cs.cogcomp.wikifier.models.LinkingProblem.deepRelationalInference(LinkingProblem.java:285)
	at edu.illinois.cs.cogcomp.wikifier.inference.InferenceEngine.annotate(InferenceEngine.java:125)
	at edu.illinois.cs.cogcomp.wikifier.ReferenceAssistant.main(ReferenceAssistant.java:89)