khuangaf/concrete

Official implementation of "CONCRETE: Improving Cross-lingual Fact Checking with Cross-lingual Retrieval" (COLING'22)

What's up!

I am a Computer Science Ph.D. candidate at the University of Illinois Urbana-Champaign, advised by Prof. Heng Ji. My research interest lies in fact-checking, corrective explanations for misinformation, and factually consistent text generation. Previously, I got my Bachelor's degree from the Hong Kong University of Science and Technology and my Master's degree from the University of Southern California.

concrete's Issues

from dpr.utils.data_utils import ShardedDataIterator, read_xict_samples_from_json_files, Tensorizer ImportError: cannot import name 'read_xict_samples_from_json_files' from 'dpr.utils.data_utils'

Hello, the following error occurs when running bash run_xict.sh. What causes it? Thanks.
from dpr.utils.data_utils import ShardedDataIterator, read_xict_samples_from_json_files, Tensorizer
ImportError: cannot import name 'read_xict_samples_from_json_files' from 'dpr.utils.data_utils'

KeyError: 'hard_negative_ctxs'

on running run_xict.sh i get the following error.

Traceback (most recent call last):
File "run_xict.py", line 600, in
main()
File "run_xict.py", line 590, in main
trainer.run_train()
File "run_xict.py", line 132, in run_train
self._train_epoch(scheduler, epoch, eval_step, train_iterator)
File "run_xict.py", line 325, in _train_epoch
shuffle_positives=args.shuffle_positive_ctx
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/dpr/models/biencoder.py", line 171, in create_biencoder_input
hard_neg_ctxs = sample["hard_negative_ctxs"]
KeyError: 'hard_negative_ctxs'

In the dataset "../../data/bbc_passages/all_ict_samples.jsonl_[0,1,2]" there is no argument 'hard_negative_ctxs'
I feel like a part of the code is missing of dpr/models/biencoder.py Can you share me the code?

ImportError: cannot import name 'read_xict_samples_from_json_files' from 'dpr.utils.data_utils'

when i run run_xict.sh it shows following error. It seems to me like you have not included dpr in this repository.

Traceback (most recent call last):
File "run_xict.py", line 32, in
from dpr.utils.data_utils import ShardedDataIterator, read_xict_samples_from_json_files, Tensorizer
ImportError: cannot import name 'read_xict_samples_from_json_files' from 'dpr.utils.data_utils' (/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/dpr/utils/data_uti$
/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects --local_rank argument to be set, please
change it to read from os.environ['LOCAL_RANK'] instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions

FutureWarning,
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 40046) of binary: /scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/bin/python
Traceback (most recent call last):
File "/home/apps/DL-CondaPy3.7/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/apps/DL-CondaPy3.7/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launch.py", line 193, in
main()
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launch.py", line 189, in main
launch(args)
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launch.py", line 174, in launch
run(args)
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/run.py", line 713, in run
)(*cmd_args)
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 131, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 261, in launch_agent
failures=result.failures,
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

KeyError: 'question'

on running run_xict.sh i get the following error.
Traceback (most recent call last):
File "run_xict.py", line 600, in
main()
File "run_xict.py", line 590, in main
trainer.run_train()
File "run_xict.py", line 132, in run_train
self._train_epoch(scheduler, epoch, eval_step, train_iterator)
File "run_xict.py", line 325, in _train_epoch
shuffle_positives=args.shuffle_positive_ctx
File "/scratch/22cs60r72/InformationRetrival/copy/CORA/mDPR/mool/lib/python3.7/site-packages/dpr/models/biencoder.py", line 172, in create_biencoder_input
question = normalize_question(sample["question"])
KeyError: 'question'

should i initialize question =[] or should i do something else ?

can not find all_ict_samples.jsonl_dev

In run_xict.sh there is a command
python -m torch.distributed.launch
--nproc_per_node 1 run_xict.py
--max_grad_norm 2.0
--encoder_model_type hf_bert
--pretrained_model_cfg bert-base-multilingual-uncased
--seed 12345 --sequence_length 256
--warmup_steps 300 --batch_size 4 --do_lower_case
--train_file "../../data/bbc_passages/all_ict_samples.jsonl_[0,1,2]"
--dev_file ../../data/bbc_passages/all_ict_samples.jsonl_dev
--output_dir xict_outputs
--checkpoint_file_name xICT_biencoder.pt
--learning_rate 2e-05 --num_train_epochs 40
--dev_batch_size 6 --val_av_rank_start_epoch 30
but I don't know where can i find all_ict_samples.jsonl_dev
Instead of this file I am using all_ict_samples-trans100.jsonl
but it gives me error
#4 (comment)

ZeroDivisionError: float division by zero

When i run run_xict.sh I get the following error:-

Traceback (most recent call last):
File "run_xict.py", line 600, in
main()
File "run_xict.py", line 590, in main
trainer.run_train()
File "run_xict.py", line 132, in run_train
self._train_epoch(scheduler, epoch, eval_step, train_iterator)
File "run_xict.py", line 363, in _train_epoch
self.validate_and_save(epoch, train_data_iterator.get_iteration(), scheduler)
File "run_xict.py", line 148, in validate_and_save
validation_loss = self.validate_nll()
File "run_xict.py", line 185, in validate_nll
total_loss = total_loss / batches
ZeroDivisionError: float division by zero

What should I do?