Box Embeddings¶
Pytorch implementation for box embeddings and box representations.
Status¶
Installation¶
Installing via pip¶
The preferred way to install Box Embeddings is via pip
. Just run pip install box-embeddings
Installing from source¶
You can also install Box Embeddings by cloning our git repository
git clone https://github.com/iesl/box-embeddings
Create a Python 3.7 or 3.8 virtual environment, and install Box Embeddings in editable mode by running:
pip install --editable . --user
pip install -r core_requirements.txt
Package Overview¶
Command |
Description |
---|---|
|
An open-source NLP research library, built on PyTorch & TensorFlow |
|
Utility modules that are used across the library |
|
Initialization modules |
|
A collection of modules to operate on boxes |
|
A collection of modules to parameterize boxes |
Citing¶
If you use simple hard boxes with surrogate loss then cite the following paper:
@inproceedings{vilnis2018probabilistic,
title={Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures},
author={Vilnis, Luke and Li, Xiang and Murty, Shikhar and McCallum, Andrew},
booktitle={Proceedings of the 56th Annual Meeting of the Association for
Computational Linguistics (Volume 1: Long Papers)},
pages={263--272},
year={2018}
}
If you use softboxes without any regularizaton the cite the following paper:
@inproceedings{
li2018smoothing,
title={Smoothing the Geometry of Probabilistic Box Embeddings},
author={Xiang Li and Luke Vilnis and Dongxu Zhang and Michael Boratko and Andrew McCallum},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=H1xSNiRcF7},
}
If you use softboxes with regularizations defined in the
Regularizations
module then cite the following paper:
@inproceedings{
patel2020representing,
title={Representing Joint Hierarchies with Box Embeddings},
author={Dhruvesh Patel and Shib Sankar Dasgupta and Michael Boratko and Xiang Li and Luke Vilnis
and Andrew McCallum},
booktitle={Automated Knowledge Base Construction},
year={2020},
url={https://openreview.net/forum?id=J246NSqR_l}
}
The code for this library can be found here.
Contributors¶
Dhruvesh Patel @dhruvdcoder
Shib Sankar Dasgupta @ssdasgupta
Michael Boratko @mboratko
Xiang (Lorraine) Li @Lorraine333
Trang Tran @trangtran72
Purujit Goyal @purujitgoyal
Tejas Chheda @tejas4888
Contributions¶
We welcome all contributions from the community to make Box Embeddings a better package. If you’re a first time contributor, we recommend you start by reading our CONTRIBUTING.md guide.
Team¶
Box Embeddings is an open-source project developed by the research team from the Information Extraction and Synthesis Laboratory at the College of Information and Computer Sciences (UMass Amherst).