akariasai / extractive_rc_by_runtime_mt Goto Github PK

Hello, I am trying to run the evaluation for the Japanese SQuAD, but I got the following error:

Traceback (most recent call last):
File "main.py", line 63, in
main()
File "main.py", line 57, in main
args.func(args)
File "/home/ubuntu/tanh/extractive_rc_by_runtime_mt/rc/evaluate_mlqa.py", line 493, in evaluate_from_args
instances = dataset_reader.read("inputdata_tmp/ja_question_v2.csv")
File "/home/ubuntu/tanh/extractive_rc_by_runtime_mt/env/lib/python3.6/site-packages/allennlp/data/dataset_readers/dataset_reader.py", line 73, in read
instances = [instance for instance in Tqdm.tqdm(instances)]
File "/home/ubuntu/tanh/extractive_rc_by_runtime_mt/env/lib/python3.6/site-packages/allennlp/data/dataset_readers/dataset_reader.py", line 73, in
instances = [instance for instance in Tqdm.tqdm(instances)]
File "/home/ubuntu/tanh/extractive_rc_by_runtime_mt/env/lib/python3.6/site-packages/tqdm/std.py", line 1081, in iter
for obj in iterable:
File "/home/ubuntu/tanh/extractive_rc_by_runtime_mt/rc/data_ml.py", line 444, in _read
trans_context_f = open(self.context_trans_file_path)
FileNotFoundError: [Errno 2] No such file or directory: 'trans_result/ja/v5/embedding/TRANS.txt.new'

I've downloaded the models jaen_nmt_params.tar.gz and rc_params.tar.gz and followed the instructions that is similar for the French SQuAD but I could not make it work. Did I miss something?

Any idea how to make it work for urdu RC and MT using similar approach
as stanfordNLP is not mature enough to identify corresponding urdu entities