Skip to content

Latest commit

 

History

History
31 lines (26 loc) · 1.3 KB

README.md

File metadata and controls

31 lines (26 loc) · 1.3 KB
Raw

Representing Syntax and Composition with Geometric Transformations

Repo contains our PyTorch implementation and training code for the DM model (Czarnowska et., al 2019). All results presented in the paper for MuRe, RotE, RefE and AttE referes to models that have been trained using the origial code provided by the authors.

Usage

python train.py -emsize 300 --neg_num 20 -epochs 5

Acknowledgements

We built our DM Dataloder on top of the one implemented by Zhenisbek Assylbekov

Cite

@inproceedings{bertolini-etal-2021-representing,
    title = "Representing Syntax and Composition with Geometric Transformations",
    author = "Bertolini, Lorenzo  and
      Weeds, Julie  and
      Weir, David  and
      Peng, Qiwei",
    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-acl.296",
    doi = "10.18653/v1/2021.findings-acl.296",
    pages = "3343--3353",
}