Parser a custom corpus
MinionAttack opened this issue · comments
Hi, first of all thanks very much for your scripts. I was dealing 2 weeks with Syntaxnet to make it work and with your files it was very easy. So, THANKS!
My question it's about parser a custom corpus. I want to parser SFU, PangLee2004 and PangLee2005. Now, I have commented:
#pretrain_parser
#evaluate_pretrained_parser
#train_parser
evaluate_parser
#copy_model
close_fd
To only execute the evaluation phase and avoid training again. I have tried to change in (corpus_folder)/context.pbtxt_p on:
input {
name: 'tagged-test-corpus'
record_format: 'conll-sentence'
Part {
file_pattern: '/home/iago/Escritorio/Probar_Parser_Google/UT_English/en-ut-test.conllu.conv'
}
}
to:
input {
name: 'tagged-test-corpus'
record_format: 'conll-sentence'
Part {
file_pattern: '/home/iago/Escritorio/Probar_Parser_Google/UT_English/en-ut-SFU.conll'
(for example)
}
}
And then execute ~$./train_p.sh -v -v but I don't know if this is the correct way. I'm doing it right?
Thanks and regards.
Ok, looking at closed issues I found that #1 and I dind't notice that was an ./test.sh!!!!
@MinionAttack aha~ i got it :)