Code for the paper 'Stylistic Variation in Part of Speech Tagging'
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
additional_analysis
code
data
figs
logs
models
utils
README.md

README.md

Part of Speech Tagging using Social Networks

Code for the paper Stylistic Variation in Part of Speech Tagging.
The dataset used in the paper is from here.

Dependencies

To run the baseline Bi-LSTM Tagger

python ensemble_train.py --no-ensemble

To run just a plain ensemble of Bi-LSTM Tagger

python ensemble_train.py --just-ensemble

To run the Social Attention Tagger using the Follow network.

python ensemble_train.py --network=follow --num-basis=4

You can run the model using either, Follow, Mention or Retweet networks, with any number of basis models.

To run the Social Attention Tagger using all the three social networks.

python ensemble_train.py --use-all-networks --num-basis=4

Please feel free to contact me if you have any questions on the code or the paper.

If you use this code, please cite our paper:

@inproceedings{balusu2018social,
  title = {Stylistic Variation in Social Media Part-of-Speech Tagging},
  author = {Murali Raghu Babu Balusu and Taha Merghani and Jacob Eisenstein},
  booktitle = {Proceedings of {NAACL} workshop on stylistic variation},
  year = {2018},
  url = {https://arxiv.org/pdf/1804.07331.pdf},
  code = {https://github.com/bmurali1994/socialnets_postagging}
}