This repo hosts the code necessary to reproduce the results of our EMNLP 2021 paper, Integrating Personalized PageRank into Neural Word Sense Disambiguation, by Ahmed ElSheikh, Michele Bevilacqua and Roberto Navigli.

This repository heavily relies on Simone's code.

@inproceedings{elsheikh-etal-2021-integrating,
    title = "Integrating Personalized PageRank into Neural Word Sense Disambiguation",
    author = "ElSheikh, Ahmed and Bevilacqua, Michele  and Navigli, Roberto",
    year = "2021",
    address = "Online",
    publisher = "Emperical Method for Natural Language Processing",
}

• make sure to have miniconda installed. if not, install it

• It is recommended to create a fresh conda env to use the repo

  - conda create -n wsd_ppr python=3.6.9 pip
  - conda activate wsd_ppr
  - git clone [email protected]:mbevila/neural-pagerank-wsd.git
  - pip install -r requirements.txt
  - pip install torch==1.5.0+cu101 torchvision==0.6.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html
  - pip install torch-sparse torch-scatter -f https://pytorch-geometric.com/whl/torch-1.5.0+cu101.html

• if it needs APEX to be installed

  git clone https://github.com/NVIDIA/apex
  cd apex
  pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

• WSD Evaluation Framework: contains the SemCor training corpus, along with the evaluation datasets from Senseval and SemEval.

Pre-preprocessed SensEmBERT+LMMS embeddings is needed to train your model:

• SensEmBERT + LMMS Embeddings

Run train.sh.

Check out predict_eval_script.sh.

This project is released under the CC-BY-NC 4.0 license (see LICENSE.txt). If you use this project, please put a link to this repo.

The authors gratefully acknowledge the support of the ERC Consolidator Grant MOUSSE No. 726487 under the European Union's Horizon 2020 research and innovation programme.