Select Git revision
04-train-argument-identification.sh
04-train-argument-identification.sh 1.38 KiB
#!/bin/bash
. config.sh
mkdir -p lrdata
ln -sf ${SEMAFOR_HOME}/file_properties.xml .
ln -sf ${SEMAFOR_HOME}/dict .
ln -sf ${SEMAFOR_HOME}/stopwords.txt lrdata
mkdir -p ${datadir}/scan
# step 1: Alphabet Creation
#$jhome/java -classpath ${classpath} -Xms4000m -Xmx4000m edu.cmu.cs.lti.ark.fn.parsing.CreateAlphabet \
# ${fefile}.frame.elements \
# ${fefile}.all.lemma.tags \
# ${datadir}/scan/cv.train.events.bin \
# ${datadir}/scan/parser.conf.unlabeled \
# ${datadir}/scan/cv.train.sentences.frame.elements.spans \
# true \
# false \
# 1 \
# null \
# ${datadir}/framenet.frame.element.map
# step 2: Caching Feature Vectors
#$jhome/java -classpath ${classpath} -Xms4000m -Xmx4000m edu.cmu.cs.lti.ark.fn.parsing.FrameFeaturesCache \
# eventsfile:${datadir}/scan/cv.train.events.bin \
# spansfile:${datadir}/scan/cv.train.sentences.frame.elements.spans \
# train-framefile:${fefile}.frame.elements \
# localfeaturescache:${datadir}/scan/featurecache.jobj
# step 3: training
$jhome/java -classpath ${classpath} -Xms8000m -Xmx8000m edu.cmu.cs.lti.ark.fn.parsing.TrainingBatchMain \
model:${datadir}/argmodel.dat \
alphabetfile:${datadir}/scan/parser.conf.unlabeled \
localfeaturescache:${datadir}/scan/featurecache.jobj \
train-framefile:${fefile}.frame.elements \
regularization:reg \
lambda:0.1 \
numthreads:4 \
binaryoverlapfactor:false