Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
pykp
script
.gitignore add post_evaluate Oct 2, 2018
LICENSE Initial commit Sep 29, 2017
README.md update README, providing testset download link. May 6, 2019
beam_search.py fix the pin-memory bug Sep 18, 2018
config.py update README, providing testset download link. May 6, 2019
evaluate.py score_dict items iteration - Fix (#26) Jul 9, 2019
logger_test.py fix bugs in multi_testset (logging, dump json of prediction) Sep 25, 2018
output.txt
predict.py run on CRC Oct 1, 2018
preprocess.py Merge branch 'multi_testset' Apr 15, 2019
preprocess_testset.py Merge branch 'multi_testset' Apr 15, 2019
requirements.txt
run_examples.sh new duplicate removing Mar 19, 2019
stat_print.py remove pred Jan 15, 2018
train.py update README, providing testset download link. May 6, 2019
train_rl.py
utils.py fix bugs in multi_testset (logging, dump json of prediction) Sep 25, 2018

README.md

seq2seq-keyphrase-pytorch

Current code is developed on PyTorch 0.4, not sure if it works on other versions.

A subset of data (20k docs) is provided here for you to test the code. Unzip and place it to data/.

If you need to train on the whole kp20k dataset, download the json data and run preprocess.py first. No trained model will be released in the near future.

Update I will not be updating this repo for a while. But please see the information below to help you run the code. Some Some test datasets in JSON format: download

  • preprocess.py: entry for preprocessing datasets in JSON format.
  • train.py: entry for training models.
  • predict.py: entry for generating phrases with well-trained models (checkpoints).

You can refer to these scripts as examples.

Note that duplicate papers that appear in popular test datasets (e.g. Inspec, SemEval) are also included in the KP20k training dataset. Please be sure to remove them before training.

You can’t perform that action at this time.