dfki-nlp / distre Goto Github PK

Thank you very much for sharing the code！

When I use the default settings (batch_size = 16), the AUC is 0.414.

But when I use the settings in the paper (batch_size = 8), the value of AUC and P@N is 0.

Am I missing something important?

Thank you !

How could I get the NYT dataset now?
Thanks.

OpenAI gpt model file cannot be found at https://cloud.dfki.de/owncloud/index.php/s/kKdpoaGikWnL4tn/download. Please tell the correct location.

I'm trying to test this method on my own dataset, and I met KeyErrors. Do you please kown how to solve this problem? Thanks a lot!

Traceback (most recent call last):
File "/data/anaconda3/envs/allennlp/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/data/anaconda3/envs/allennlp/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/run.py", line 18, in
main(prog="allennlp")
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/commands/init.py", line 72, in main
args.func(args)
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/commands/train.py", line 111, in train_model_from_args
args.force)
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/commands/train.py", line 142, in train_model_from_file
return train_model(params, serialization_dir, file_friendly_logging, recover, force)
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/commands/train.py", line 298, in train_model
model = Model.from_params(vocab=vocab, params=params.pop('model'))
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/common/from_params.py", line 274, in from_params
return subclass.from_params(params=params, **extras)
File "/data/anaconda3/envs/allennlp/lib/python3.6/site-packages/allennlp/common/from_params.py", line 287, in from_params
return cls(**kwargs) # type: ignore
File "/data/DISTRE/tre/model.py", line 235, in init
self.na_idx = self.vocab.get_token_to_index_vocabulary('labels')['NA']
KeyError: 'NA'

page not found

1. create the protobuf files: protoc --proto_path=. --python_out=. Document.proto
   Where is the file of Document.proto?

2)convert the protobuf files to json: python protobuf2json.py .
Where is the file of protobuf2json.py?

Thank you!

Hi:

Thanks for the awesome contributions.

I notice there is sorting keys params in your config, but it seems like _create_batches of BagIterator doesn't use those keys to sort Bags/Instances in your repo.

So I wonder if you actually implement the sorting. If you do, how do you implement the sorting?

thankyou

Hi, I wonder how you obtain the sentence representation.
In your paper:

A sentence representation is obtained by feeding the token sequence xi of a sentence to the pre-trained model and using the last state of the final state representation hL as its representation si.

Is the sentence representations are the last state of '[CLS]' or something else? I am confused about that.
Would you please explain that for me? Thanks a lot.

Best