mengf1/pal

Policy based Active Learning with DQN (EMNLP-2017)

pal's Issues

The link of "Crosslingual word embeddings and corpora" in readme is broken

Hi,
Thanks for your code releasing.
But the link of "Crosslingual word embeddings and corpora" in readme is broken.
Could you please update the data urls?

Thanks

Cannot find embedding files online

Hello,

Thanks for the code release!
Did you train your own embeddings or found them on the website?
It seems that there is no file en.emb or nl.emb available on http://128.2.220.95/multilingual

Thanks,

Ismini

Data download problem

I found that the data download website cannot open, I do not know how to get the data. Is it possible that you send me the data through email?

Data links seem to be broken again

From where can I download the data (en.train;en.testa;en.testb) and embeddings (en.emb)? I've tried looking around and it's not clear to me where I can find them on the pages pointed to in the README.

Thanks!

issue in q-learning

Hi,
In the paper, as training Q network, the expected Q_value (y) should be reward + r * Q_value_next_state. However, in this code, it seems to be Q_value_this_state. Is there something wrong as code released? Thank you.

Can you share the data folder?

I want to understand your implementation, it would be great if the en and de files were available.

can't reproduce because of data issue

Hi,
Thank you for your code releasing.
Could you also upload your data folder? The link in readme is broken.
Also it's still not clear which embedding file should be used. is that multiCCA one ?

Command line provided in README.md fails

I thought your paper was very interesting, so I decided to look at your code. Unfortunately, I have not been able to get it running. Any advice would be appreciated. See below.

Thanks,
Jay
[email protected]

The application appears to be confused between tensorflow flags and your application flags.

$ python launcher_ner_bilingual.py --agent "CNNDQN" --episode 10000 --budget 1000 --train "en.train;en.testa;en.testb;en.emb;en.model.saved" --test "de.train;de.testa;de.testb;de.emb;de.model.saved"

Traceback (most recent call last):
File "launcher_ner_bilingual.py", line 15, in
FLAGS._parse_flags()
File "/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/tensorflow/python/platform/flags.py", line 84, in getattr
wrapped(_sys.argv)
File "/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/absl/flags/_flagvalues.py", line 630, in call
name, value, suggestions=suggestions)
absl.flags._exceptions.UnrecognizedFlagError: Unknown command line flag 'agent'