java - How to train Stanford Parser for persian? -

i want use stanford nlp coref persian. (training model next question;) ) able that, need use these annotators: "tokenize,ssplit,pos,lemma,ner,parse,mention,coref"

i have trained models pos , ner. problem is, can not train model parser.

i using uppsala persian dependency treebank (updt) in .conll format. (tab separated) here part of training-data-file.conll:

1 اولین _ adj adj_sup sup 2 amod

2 سیاره _ n n_sing sing 7 nsubjpass

3 خارج _ p p p 2 prep

4 از _ p p p 3 mwe

5 منظومه _ n n_sing sing 3 pobj

6 شمسی _ adj adj adj 5 amod

first tried train parser, using "edu.stanford.nlp.parser.lexparser.lexicalizedparser" following arguments : "-train parser-train-file.conll" output :

slf4j: failed load class "org.slf4j.impl.staticloggerbinder". slf4j: defaulting no-operation (nop) logger implementation slf4j: see http://www.slf4j.org/codes.html#staticloggerbinder further details. done [read 0 trees]. time elapsed: 2 ms useunknownwordsignatures 0 smoothinunknownsthreshold 100 smartmutation false useunicodetype false unknownsuffixsize 1 unknownprefixsize 1 flexitag false usesignatureforknownsmoothing false wordclassesfile null parserparams edu.stanford.nlp.parser.lexparser.englishtreebankparserparams forcecnf false dopcfg true dodep true freedependencies false directional true genstop true distance true coarsedistance false dctags true nprune false done. time elapsed: 5 ms done. time elapsed: 6 ms done. time elapsed: 5 ms done time elapsed: 0 ms done. time elapsed: 3 ms useunknownwordsignatures 0 smoothinunknownsthreshold 100 smartmutation false useunicodetype false unknownsuffixsize 1 unknownprefixsize 1 flexitag false usesignatureforknownsmoothing wordclassesfile null parserparams edu.stanford.nlp.parser.lexparser.englishtreebankparserparams forcecnf false dopcfg true dodep true freedependencies false directional true genstop true distance true coarsedistance false dctags true nprune false exception in thread "main" java.lang.arrayindexoutofboundsexception: -1 @ edu.stanford.nlp.parser.lexparser.exhaustivepcfgparser.parse(exhaustivepcfgparser.java:477) @ edu.stanford.nlp.parser.lexparser.lexicalizedparserquery.parseinternal(lexicalizedparserquery.java:271) @ edu.stanford.nlp.parser.lexparser.lexicalizedparserquery.parse(lexicalizedparserquery.java:638) @ edu.stanford.nlp.parser.lexparser.lexicalizedparser.main(lexicalizedparser.java:1509) @ sun.reflect.nativemethodaccessorimpl.invoke0(native method) @ sun.reflect.nativemethodaccessorimpl.invoke(nativemethodaccessorimpl.java:62) @ sun.reflect.delegatingmethodaccessorimpl.invoke(delegatingmethodaccessorimpl.java:43) @ java.lang.reflect.method.invoke(method.java:498) @ com.intellij.rt.execution.application.appmain.main(appmain.java:144) 

then tried train parser, using "edu.stanford.nlp.parser.nndep.dependencyparser" program arguments : "-trainfile parser-train-file.conll -model parser-model.ser.gz"

when run program, output below:

slf4j: failed load class "org.slf4j.impl.staticloggerbinder". slf4j: defaulting no-operation (nop) logger implementation slf4j: see http://www.slf4j.org/codes.html#staticloggerbinder further details. #trees: 0 0 tree(s) illegal (nan%). 0 tree(s) legal have multiple roots (nan%). 0 tree(s) legal not projective (nan%). random generator initialized seed 1501050216053 language = universalenglish trainingthreads = 1 wordcutoff = 1 initrange = 0.010 maxiter = 20000 batchsize = 10000 adaeps = 1.0e-06 adaalpha = 0.010 regparameter = 1.0e-08 dropprob = 0.50 hiddensize = 200 embeddingsize = 50 numprecomputed = 100000 evalperiter = 100 cleargradientsperiter = 0 saveitermediate = true unlabeled = false cpos = false nopunc = true dowordembeddinggradupdate = true percent necessary pre-compute: 0.000000% percent necessary pre-compute: 0.000000% percent necessary pre-compute: 0.000000% percent necessary pre-compute: 0.000000% percent necessary pre-compute: 0.000000% percent necessary pre-compute: 0.000000% ... (this goes on minutes!!!) 

i confused. have followed written on "https://nlp.stanford.edu/software/parser-faq.shtml" , "https://nlp.stanford.edu/software/nndep.shtml".

i appreciate if can show me clue.