Need help with HeterSumGraph?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

133 Stars 24 Forks 15 Commits 6 Opened issues


Code for ACL2020 paper "Heterogeneous Graph Neural Networks for Extractive Document Summarization"

Services available


Need anything else?

Contributors list

# 169,873
14 commits


Code for ACL 2020 paper: Heterogeneous Graph Neural Networks for Extractive Document Summarization

fastNLP version will come soon.

Some code are borrowed from PG and Transformer. Thanks for their work.


  • python 3.5+
  • PyTorch 1.0+
  • DGL 0.4
  • rouge 1.0.0
    • A full Python Implementation of the ROUGE Metric which is used in validation phrase
  • pyrouge 0.1.3

  • others

    • nltk
    • numpy
    • sklearn


We have preprocessed CNN/DailyMail, NYT50 and Multi-News datasets for TF-IDF features used in the graph creation, which you can find here.

For CNN/DailyMail and Multi-News, we also provide the json-format datasets in this link. However, due to the license, NYT(The New York Times Annotated Corpus) can only be available from LDC. And we follow the preprocessing code of Durrett et al. (2016) to get the NYT50 datasets.

The example looks like this:

  "text":["deborah fuller has been banned from keeping animals ... 30mph",...,"a dog breeder and exhibitor... her dogs confiscated"],
  "summary":["warning : ... at a speed of around 30mph",... ,"she was banned from ... and given a curfew "],

and each line in the file is an example. For the text key, the value can be list of string (single-document) or list of list of string (multi-document). The example in training set can ignore the summary key since we only use label during the training phrase. All strings need be lowercase and tokenized by Stanford Tokenizer, and nltk.sent_tokenize is used to get sentences.

After getting the standard json format, you can prepare the dataset for the graph by in the project directory. The processed files will be put under the cache directory.

The default file names for training, validation and test are: train.label.jsonl, val.label.jsonl and test.label.jsonl. If you would like to use other names, please change the corresponding names in, Line 321-322 in and Line 188 in (Default names is recommended)


For training, you can run commands like this:

python --cuda --gpu 0 --data_dir  --cache_dir  --embedding_path  --model [HSG|HDSG] --save_root  --log_root  --lr_descent --grad_clip -m 3

We also provide our checkpoints on CNN/DailyMail, NYT50 and Multi-News in this link. Besides, the outputs can be found here(NYT50 has been removed due to its license).


For evaluation, the command may like this:

python --cuda --gpu 0 --data_dir  --cache_dir  --embedding_path   --model [HSG|HDSG] --save_root  --log_root  -m 3 --test_model multi --use_pyrouge

Some options:

  • use_pyrouge: whether to use pyrouge for evaluation. Default is False (which means rouge).
    • Please change Line17-18 in tools/ to your own ROUGE path and temp file path.
  • limit: whether to limit the output to the length of gold summaries. This option is only set for evaluation on NYT50 (which uses ROUGE-recall instead of ROUGE-f). Default is False.
  • blocking: whether to use Trigram blocking. Default is False.
  • save_label: only save label and do not calculate ROUGE. Default is False.

To load our checkpoint for evaluation, you should put it under the save_root/eval/ and make the name for testmodel to start with eval. For example, if your saveroot is "checkpoints", then the checkpoint "cnndm.ckpt" should be put under "checkpoints/eval" and the test_model is evalcnndm.ckpt.

ROUGE Installation

In order to get correct ROUGE scores, we recommend using the following commands to install the ROUGE environment:

sudo apt-get install libxml-perl libxml-dom-perl
pip install git+git://
export PYROUGE_HOME_DIR=the/path/to/RELEASE-1.5.5
pyrouge_set_rouge_path $PYROUGE_HOME_DIR

You can refer to for RELEASE-1.5.5 and remember to build Wordnet 2.0 instead of 1.6 in RELEASE-1.5.5/data:

cd $PYROUGE_HOME_DIR/data/WordNet-2.0-Exceptions/
./ . exc WordNet-2.0.exc.db
cd ../
ln -s WordNet-2.0-Exceptions/WordNet-2.0.exc.db WordNet-2.0.exc.db

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.