Hi, can you check if the line
inhaled corticosteroids ||| inhalative Kortikoichaemic ||| ischämische ||| mono other really occurs in the extract.o file? It should only have source / target / reordering status, not 4 entries. Did something go wrong when the extract file was created (out of disk space?). Do you have "|||" in the corpus? Did you try re-running extract & build reorder? -phi On Tue, Mar 28, 2017 at 10:03 AM, Anna Kupś <aniak...@gmail.com> wrote: > > Hi, > > I got the following error while using Experiment Management System: > > ==> TRAINING_build-reordering.3 <== > > PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/ > sbin:/bin:/snap/bin:/snap/bin" > cd /root/working/experiments > echo 'starting at '`date`' on '`hostname` > mkdir -p /root/working/experiments/training > > /root/mosesdecoder/scripts/training/train-model.perl -mgiza -mgiza-cpus 8 > -dont-zip -first-step 7 -last-step 7 -external-bin-dir > /root/mosesdecoder/tools -f en -e de -alignment grow-diag-final-and > -reordering msd-bidirectional-fe -extract-file > /root/working/experiments/model/extract.2 > -reordering-table /root/working/experiments/model/reordering-table.3 > > echo 'finished at '`date` > touch /root/working/experiments/steps/3/TRAINING_build-reordering.3.DONE > > ==> TRAINING_build-reordering.3.INFO <== > lexicalized-reordering = msd-bidirectional-fe > INPUT = USED /root/working/experiments/model/extract.2 > # reuse run 2 for TRAINING:extract-phrases > > ==> TRAINING_build-reordering.3.STDERR <== > Using SCRIPTS_ROOTDIR: /root/mosesdecoder/scripts > using gzip > (7) learn reordering model @ Tue Mar 28 12:19:55 CEST 2017 > (7.1) [no factors] learn reordering model @ Tue Mar 28 12:19:55 CEST 2017 > (7.2) building tables @ Tue Mar 28 12:19:55 CEST 2017 > Executing: /root/mosesdecoder/scripts/../bin/lexical-reordering-score > /root/working/experiments/model/extract.2.o.sorted.gz 0.5 > /root/working/experiments/model/reordering-table.3. --model "wbe msd > wbe-msd-bidirectional-fe" > Lexical Reordering Scorer > scores lexical reordering models of several types (hierarchical, > phrase-based and word-based-extraction > > ==> TRAINING_build-reordering.3.STDOUT <== > starting at Di 28. Mär 12:19:54 CEST 2017 on machine-VirtualBox > > ==> TRAINING_build-reordering.3.STDERR <== > terminate called after throwing an instance of 'FileFormatException' > what(): phrase-extract/lexical-reordering/score.cpp:260 in void > split_line(const StringPiece&, StringPiece&, StringPiece&, StringPiece&, > StringPiece&, StringPiece&, float&) threw FileFormatException because > `errIndex == next.data()'. > Invalid extract file format: inhaled corticosteroids ||| inhalative > Kortikoichaemic ||| ischämische ||| mono other > Aborted (core dumped) > Exit code: 134 > *ERROR: Lexical reordering scoring failed at > /root/mosesdecoder/scripts/training/train-model.perl line 1924.* > > Does someone know how to get rid of that problem? > > Thanks in advance and best regards, > Anna > > -- > Anna Kupś > +48 782 823 850 <+48%20782%20823%20850> | www.linkedin.com/in/annakups > > _______________________________________________ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support > >
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support