Problem for artical about bertsum HOT 14 CLOSED

I cannot help you with the information you provided. please always patse your commsnds.

from bertsum.

problem1:
the commend for train classifier is:
python train.py -mode train -encoder classifier -dropout 0.1 -bert_data_path /home/test/WangHN/BertSum-master/bert_data/cnndm -model_path /home/test/WangHN/BertSum-master/models/bert_classifier -lr 2e-3 -visible_gpus 0,1,2 -gpu_ranks 0,1,2 -world_size 3 -report_every 50 -save_checkpoint_steps 1000 -batch_size 3000 -decay_method noam -train_steps 50000 -accum_count 2 -log_file /home/test/WangHN/BertSum-master/logs/bert_classifier -use_interval true -warmup_steps 10000
for test classifier is:
python train.py -mode validate -bert_data_path /home/test/WangHN/BertSum-master/bert_data/cnndm -model_path /home/test/WangHN/BertSum-master/models/bert_classifier -visible_gpus 1 -gpu_ranks 0 -batch_size 30000 -log_file /home/test/WangHN/BertSum-master/logs/Evaluation/bert_classifier -result_path /home/test/WangHN/BertSum-master/results/classifier/cnndm -test_all -block_trigram true

the log file's results are what I provide above , the rouge score is low, this is also true in another （rnn and transformer）

problem2:
for the summary results, how can I find the original article ,for example ref.83.txt and can.83.txt's original article?

from bertsum.

could you run -mode lead to see if the data is correct

from bertsum.

how to do this

from bertsum.

python train.py -mode lead -bert_data_path ../../../bertabs/bert_data/cnndm -visible_gpus -1 -batch_size 30000 -log_file cnndm_lead -result_path ../results/cnndm_lead -block_trigram false

from bertsum.

dont have the mode lead.
I also think the problem may be model training, need I retraining the model?

from bertsum.

please checkout to dev branch and run lead

from bertsum.

sorry，where is dev branch

from bertsum.

please google for "check out branches on github"

from bertsum.

I run mode -lead ，got this results， .

from bertsum.

apparently the data is wrong. how do you process the data?

from bertsum.

I process the data by the commend you provide，
Put the CNN story file and the daily mail story file under one file，using the Stanford CoreNLP version:3.7.0
then got the sentence splitting and token, just follow the step 3,4,5 , then got the bert_data file.

from bertsum.

please past some parts of the json file in got from format_to_lines

from bertsum.

or could you rerun the preprocessing process and calculate lead

from bertsum.