2021-01-14 08:07:24 +01:00
|
|
|
trainFileList = /u/nlp/data/ner/german/german-ner-w-hyphens.train.conll,/u/nlp/data/ner/german/german-ner-extra-eval-w-hyphens.train.conll
|
|
|
|
testFile = /u/nlp/data/ner/german/german-ner-w-hyphens.dev.conll
|
|
|
|
serializeTo = /u/nlp/data/ner/german/models/german.distsim.crf.ser.gz
|
|
|
|
|
|
|
|
type=crf
|
|
|
|
|
|
|
|
# distSimLexicon = /u/nlp/data/german/ner/hgc_175m_600
|
|
|
|
distSimLexicon = /u/nlp/data/german/ner/2016/hgc-175M-600
|
|
|
|
# right options for new hgc_175m_600
|
|
|
|
distSimFileFormat = alexClark
|
|
|
|
unknownWordDistSimClass = 599
|
|
|
|
useDistSim = true
|
|
|
|
numberEquivalenceDistSim = false
|
|
|
|
casedDistSim = true
|
|
|
|
|
|
|
|
# Now using stripped 2 column files so can add extra datasets!
|
|
|
|
map = word=0,answer=1
|
|
|
|
|
|
|
|
encoding = utf-8
|
|
|
|
# saveFeatureIndexToDisk = true # now buggy but unnecessary
|
|
|
|
mergeTags = false
|
|
|
|
useTitle = false
|
|
|
|
|
|
|
|
useClassFeature=true
|
|
|
|
useWord=true
|
|
|
|
useNGrams=true
|
|
|
|
noMidNGrams=true
|
|
|
|
# Having no maxNGramLeng seemed to work marginally better, but omitted for efficiency
|
|
|
|
maxNGramLeng=6
|
|
|
|
usePrev=true
|
|
|
|
useNext=true
|
|
|
|
useLongSequences=true
|
|
|
|
useSequences=true
|
|
|
|
usePrevSequences=true
|
|
|
|
useTypeSeqs=true
|
|
|
|
useTypeSeqs2=true
|
|
|
|
useTypeySequences=true
|
|
|
|
# Including useOccurrencePatterns increased scores really marginally (could even disappear now we have weaker regularization)
|
|
|
|
useOccurrencePatterns=true
|
|
|
|
useLastRealWord=true
|
|
|
|
useNextRealWord=true
|
|
|
|
normalize=true
|
|
|
|
# using chris4 instead hurts in most recent experiment. Earlier, an experiment had seemed to show the opposite.
|
|
|
|
wordShape=chris2useLC
|
|
|
|
useDisjunctive=true
|
|
|
|
# Width 5 works a little better than 4
|
|
|
|
disjunctionWidth=5
|
|
|
|
|
|
|
|
maxLeft=1
|
|
|
|
readerAndWriter=edu.stanford.nlp.sequences.ColumnDocumentReaderAndWriter
|
|
|
|
useObservedSequencesOnly=true
|
|
|
|
useQN = true
|
|
|
|
QNsize = 15
|
|
|
|
# sigma 20 works better than sigma 5, which is MUCH better than sigma 1; that was the limit of hyperparameter optimization
|
|
|
|
# On the basic CoNLL dataset (no distsim, no extra data), sigma=50 is a bit better still (by 0.13 F1)
|
|
|
|
sigma = 20
|
|
|
|
|
|
|
|
# For making faster (less features); changing this to 0.025 doesn't improve performance
|
|
|
|
featureDiffThresh=0.05
|
|
|
|
|
|
|
|
# evaluateIOB=true
|
|
|
|
|
|
|
|
# other notes
|
|
|
|
# even though useTaggySequences will use distsim rather than POS sequences, turning it on didn't help
|
|
|
|
# adding useWordPairs doesn't seem to help. (Getting them anyway in an edge feature.)
|