This code is for EMNLP 2019 paper Text Summarization with Pretrained Encoders

Results on CNN/DailyMail (20/8/2019):

Python version: This code is in Python3.6

Package Requirements: torch pytorch_transformers tensorboardX multiprocess pyrouge

Some codes are borrowed from ONMT(https://github.com/OpenNMT/OpenNMT-py)

download https://drive.google.com/open?id=1BWBN1coTWGBqrWoOfRc5dhojPHhatbYs

download https://drive.google.com/open?id=1DN7ClZCCXsk2KegmC6t4ClBwtAf5galI

unzip the zipfile and put all .pt files into bert_data

Download and unzip the stories directories from here for both CNN and Daily Mail. Put all .story files in one directory (e.g. ../raw_stories)

We will need Stanford CoreNLP to tokenize the data. Download it here and unzip it. Then add the following command to your bash_profile:

export CLASSPATH=/path/to/stanford-corenlp-full-2017-06-09/stanford-corenlp-3.8.0.jar

replacing /path/to/ with the path to where you saved the stanford-corenlp-full-2017-06-09 directory.

python preprocess.py -mode tokenize -raw_path RAW_PATH -save_path TOKENIZED_PATH

• RAW_PATH is the directory containing story files (../raw_stories), JSON_PATH is the target directory to save the generated json files (../merged_stories_tokenized)

python preprocess.py -mode format_to_lines -raw_path RAW_PATH -save_path JSON_PATH -n_cpus 1 -use_bert_basic_tokenizer false -map_path MAP_PATH

• RAW_PATH is the directory containing tokenized files (../merged_stories_tokenized), JSON_PATH is the target directory to save the generated json files (../json_data/cnndm), MAP_PATH is the directory containing the urls files (../urls)

python preprocess.py -mode format_to_bert -raw_path JSON_PATH -save_path BERT_DATA_PATH  -lower -n_cpus 1 -log_file ../logs/preprocess.log

• JSON_PATH is the directory containing json files (../json_data), BERT_DATA_PATH is the target directory to save the generated binary files (../bert_data)

First run: For the first time, you should use single-GPU, so the code can download the BERT model. Use -visible_gpus -1, after downloading, you could kill the process and rerun the code with multi-GPUs.

python train.py -task ext -mode train -bert_data_path BERT_DATA_PATH -ext_dropout 0.1 -model_path MODEL_PATH -lr 2e-3 -visible_gpus 0,1,2 -report_every 50 -save_checkpoint_steps 1000 -batch_size 3000 -train_steps 50000 -accum_count 2 -log_file ../logs/ext_bert_cnndm -use_interval true -warmup_steps 10000 -max_pos 512

python train.py  -task abs -mode train -bert_data_path BERT_DATA_PATH -dec_dropout 0.2  -model_path MODEL_PATH -sep_optim true -lr_bert 0.002 -lr_dec 0.2 -save_checkpoint_steps 2000 -batch_size 140 -train_steps 200000 -report_every 50 -accum_count 5 -use_bert_emb true -use_interval true -warmup_steps_bert 20000 -warmup_steps_dec 10000 -max_pos 512 -visible_gpus 0,1,2,3  -log_file ../logs/abs_bert_cnndm

python train.py  -task abs -mode train -bert_data_path BERT_DATA_PATH -dec_dropout 0.2  -model_path MODEL_PATH -sep_optim true -lr_bert 0.002 -lr_dec 0.2 -save_checkpoint_steps 2000 -batch_size 140 -train_steps 200000 -report_every 50 -accum_count 5 -use_bert_emb true -use_interval true -warmup_steps_bert 20000 -warmup_steps_dec 10000 -max_pos 512 -visible_gpus 0,1,2,3 -log_file ../logs/abs_bert_cnndm  -load_from_extractive EXT_CKPT   

• EXT_CKPT is the saved .pt checkpoint of the extractive model.

 python train.py -task abs -mode validate -batch_size 3000 -test_batch_size 500 -bert_data_path BERT_DATA_PATH -log_file ../logs/val_abs_bert_cnndm -model_path MODEL_PATH -sep_optim true -use_interval true -visible_gpus 1 -max_pos 512 -max_length 200 -alpha 0.95 -min_length 50 -result_path ../logs/abs_bert_cnndm 

• -mode can be {validate, test}, where validate will inspect the model directory and evaluate the model for each newly saved checkpoint, test need to be used with -test_from, indicating the checkpoint you want to use
• MODEL_PATH is the directory of saved checkpoints
• use -mode valiadte with -test_all, the system will load all saved checkpoints and select the top ones to generate summaries (this will take a while)