Open zhijing-jin opened 1 year ago
Hi @zhijing-jin , thanks for reporting this bug. It's probably due to the famous "text degeneration" problem of many seq2seq models. After https://github.com/emorynlp/elit/commit/0dad49e587ce415e867f1c6aaf39a5261ebde9c4 is released, you can set beam_size=4, no_repeat_ngram_size=4
to mitigate it (probably tune no_repeat_ngram_size
on some dev set).
parser(sent, beam_size=4, no_repeat_ngram_size=4)
(z1 / equal-01
:ARG1 (z2 / product-of
:op1 300
:op2 10
:op3 (z3 / baggy))
:ARG2-of (z4 / equal-01
:ARG1 (z5 / mask
:mod (z6 / face)
:mod (z7 / baggie))))
Though the result is still not perfect, it looks better now.
Great, thank you! This is really helpful :)!!
Hi thanks for making this wonderful package. Very user-friendly and easy to use!
I am using the AMR parsing function. And this post is to report that there are some failure cases, where the generated AMR is quite extreme:
The generated AMR has thousands of variables, up to "x2000". And it seems to enter into a recurrent loop as follows:
It's just a bug for your record.