-
Notifications
You must be signed in to change notification settings - Fork 51
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
119 additions
and
3 deletions.
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,53 @@ | ||
# Conll config file | ||
|
||
# Required fields | ||
configFilename finalSystemBILOU | ||
pathToModelFile data/Models/CoNLL | ||
taggingEncodingScheme BILOU | ||
tokenizationScheme DualTokenizationScheme | ||
|
||
# Optional fields | ||
beamSize 5 | ||
forceNewSentenceOnLineBreaks true | ||
labelTypes PER ORG LOC MISC | ||
logging false | ||
# debuggingLogPath irrelevant | ||
inferenceMethod GREEDY | ||
normalizeTitleText false | ||
pathToTokenNormalizationData brown-clusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt | ||
predictionConfidenceThreshold -1 | ||
sortLexicallyFilesInFolders true | ||
thresholdPrediction false | ||
treatAllFilesInFolderAsOneBigDocument true | ||
debug true | ||
|
||
# Features | ||
Forms 1 | ||
Capitalization 1 | ||
WordTypeInformation 1 | ||
Affixes 1 | ||
PreviousTag1 1 | ||
PreviousTag2 1 | ||
PreviousTagPatternLevel1 1 | ||
PreviousTagPatternLevel2 1 | ||
AggregateContext 0 | ||
AggregateGazetteerMatches 0 | ||
PrevTagsForContext 1 | ||
PredictionsLevel1 1 | ||
|
||
# Feature groups | ||
BrownClusterPaths 1 | ||
isLowercaseBrownClusters false false false | ||
pathsToBrownClusters brown-clusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt brown-clusters/brownBllipClusters brown-clusters/brown-rcv1.clean.tokenized-CoNLL03.txt-c1000-freq1.txt | ||
minWordAppThresholdsForBrownClusters 5 5 5 | ||
|
||
GazetteersFeatures 1 | ||
pathToGazetteersLists ner-ext/KnownLists | ||
|
||
WordEmbeddings 0 | ||
# pathsToWordEmbeddings WordEmbedding/model-2280000000.LEARNING_RATE=1e-08.EMBEDDING_LEARNING_RATE=1e-07.EMBEDDING_SIZE=50.gz | ||
# embeddingDimensionalities 50 | ||
# minWordAppThresholdsForEmbeddings 0 | ||
# normalizationConstantsForEmbeddings 1.0 | ||
# normalizationMethodsForEmbeddings OVERALL | ||
# isLowercaseWordEmbeddings false |
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 |
---|---|---|
@@ -0,0 +1,6 @@ | ||
# This is a stripped down and minimal file | ||
configFilename finalSystemBILOU | ||
taggingEncodingScheme BILOU | ||
pathToModelFile data/Models/CoNLL | ||
tokenizationScheme LbjTokenizationScheme | ||
|
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 |
---|---|---|
@@ -0,0 +1,53 @@ | ||
# Ontonotes config file | ||
|
||
# Required fields | ||
configFilename Ontonotes | ||
pathToModelFile data/Models/Ontonotes | ||
taggingEncodingScheme BILOU | ||
tokenizationScheme DualTokenizationScheme | ||
|
||
# Optional fields | ||
beamSize 5 | ||
forceNewSentenceOnLineBreaks true | ||
labelTypes TIME LAW GPE NORP LANGUAGE PERCENT FAC PRODUCT ORDINAL LOC PERSON WORK_OF_ART MONEY DATE EVENT QUANTITY ORG CARDINAL | ||
logging false | ||
# debuggingLogPath irrelevant | ||
inferenceMethod GREEDY | ||
normalizeTitleText false | ||
pathToTokenNormalizationData brown-clusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt | ||
predictionConfidenceThreshold -1 | ||
sortLexicallyFilesInFolders true | ||
thresholdPrediction false | ||
treatAllFilesInFolderAsOneBigDocument false | ||
debug true | ||
|
||
# Features | ||
Forms 1 | ||
Capitalization 1 | ||
WordTypeInformation 1 | ||
Affixes 1 | ||
PreviousTag1 1 | ||
PreviousTag2 1 | ||
PreviousTagPatternLevel1 1 | ||
PreviousTagPatternLevel2 1 | ||
AggregateContext 0 | ||
AggregateGazetteerMatches 0 | ||
PrevTagsForContext 1 | ||
PredictionsLevel1 1 | ||
|
||
# Feature groups | ||
BrownClusterPaths 1 | ||
isLowercaseBrownClusters false false false | ||
pathsToBrownClusters brown-clusters/brown-english-wikitext.case-intact.txt-c1000-freq10-v3.txt brown-clusters/brownBllipClusters brown-clusters/brown-rcv1.clean.tokenized-CoNLL03.txt-c1000-freq1.txt | ||
minWordAppThresholdsForBrownClusters 5 5 5 | ||
|
||
GazetteersFeatures 1 | ||
pathToGazetteersLists ner-ext/KnownLists | ||
|
||
WordEmbeddings 0 | ||
# pathsToWordEmbeddings WordEmbedding/model-2280000000.LEARNING_RATE=1e-08.EMBEDDING_LEARNING_RATE=1e-07.EMBEDDING_SIZE=50.gz | ||
# embeddingDimensionalities 50 | ||
# minWordAppThresholdsForEmbeddings 0 | ||
# normalizationConstantsForEmbeddings 1.0 | ||
# normalizationMethodsForEmbeddings OVERALL | ||
# isLowercaseWordEmbeddings false |