Error with Embeddings

[yongzx]

When I run ./frameid.sh -m train -x 101 after conversion and preprocessing with
./preprocess.sh -x 101 -t nlp4j -d bmst -p semafor
I encounter this error:

Preparing files for frame identification...
Converting to .flattened format for the SEMAFOR parser...
Processing file: /home/zxy485/zxy485gallinahome/week1/pyfn/scripts/../experiments/xp_101/frameid/data/corpora/test.sentences.conllx
Done
Training frame identification on all models...
Using TensorFlow backend.
['/home/zxy485/zxy485gallinahome/week1/pyfn/scripts/../lib/eacl2017-oodFrameNetSRL/simpleFrameId/main.py', 'train', '/home/zxy485/zxy485gallinahome/week1/pyfn/scripts/../experiments/xp_101/frameid']
Traceback (most recent call last):
  File "/home/zxy485/zxy485gallinahome/week1/pyfn/scripts/../lib/eacl2017-oodFrameNetSRL/simpleFrameId/main.py", line 186, in <module>
    EMBEDDINGS_NAME = sys.argv[3]
IndexError: list index out of range
Done

It seems like the embedding file is missing. May I know where to seek for the embedding file? Thank you!

[akb89]

Thanks for reporting this! I recently added two new scripts (frameid.embed.shand open-sesame.embed.sh) to be able to specify which embeddings to use is both frame and argument identification and I forgot to update the frameid.sh script accordingly, which introduced a bug.
It's now fixed, you can download the updated scripts via:

wget http://129.194.21.122/~kabbach/pyfn/scripts.7z

or directly on Github by downloading files under https://github.com/akb89/pyfn/tree/master/scripts.
I have also updated the README to add the specific package versions required by SIMPLEFRAMEID, as I realized it no longer worked when installing the latest dependencies. You can install them via:

pip install keras==2.0.6 lightfm==1.13 sklearn numpy==1.13.1 networkx==1.11 tensorflow==1.3.0

before running:

./frameid.sh -m train -x 101