This is the python3 code for the paper "Open Domain Event Extraction Using Neural Latent Variable Models" in ACL 2019.
Modify the Line 24 and 25 in cache_features.py
.
The fine-tune process need 2 * GTX 1080Ti, if the fine-tune process is costly or somehow failed to complete, please use the initial parameters in allennlp.
Please note that it is optional to finetune the ELMo model if you just want to complete the whole procedure or use the model in somewhere else.
The data is HERE.
- run the dataprocessor
- run
sudo chown [YOUR_UERS] [PROCESSED_DIR]
and specify the directories insetting.yaml
manually - run
pip install -r requirements.txt
to install required packages - run
python cache_features.py
- run
python train_avitm.py
- run
python generate_slot_topN.py
- run
python decode.py
- run
cd slotcoherence && ./run-oc.sh
- run
visualize_test.ipynb
*.json.pt
: cached features of ODEE input*.json.answer
: decoded full results of a news group*.json.template
: decoded template of a news group*.json.events.topN
: decoded top-N events of a news group*.json.labeled
: labeled events of test splitslotcoherence/slot_head_words.txt
: generated topN head words for each slot
Please cite our ACL 2019 paper:
@proceedings{liu2019open,
title={Open Domain Event Extraction Using Neural Latent Variable Models},
author={Liu, Xiao and Huang, Heyan and Zhang, Yue},
booktitle={Proceedings of Annual Meeting of the Association for Computational Linguistics},
year={2019},
publisher={Association for Computational Linguistics}
}