Box Embeddings: An open-source library for representation learning using geometric structures

Tejas Chheda, Purujit Goyal, Trang Tran, Dhruvesh Patel, Michael Boratko, Shib Sankar Dasgupta, Andrew McCallum


Abstract
A fundamental component to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with more geometric structure (eg. distributions, complex or hyperbolic vectors, or regions such as cones, disks, or boxes) have been explored for their alternative inductive biases and additional representational capacity. In this work, we introduce Box Embeddings, a Python library that enables researchers to easily apply and extend probabilistic box embeddings. Fundamental geometric operations on boxes are implemented in a numerically stable way, as are modern approaches to training boxes which mitigate gradient sparsity. The library is fully open source, and compatible with both PyTorch and TensorFlow, which allows existing neural network layers to be replaced with or transformed into boxes easily. In this work, we present the implementation details of the fundamental components of the library, and the concepts required to use box representations alongside existing neural network architectures.
Anthology ID:
2021.emnlp-demo.24
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
203–211
Language:
URL:
https://aclanthology.org/2021.emnlp-demo.24
DOI:
10.18653/v1/2021.emnlp-demo.24
Bibkey:
Cite (ACL):
Tejas Chheda, Purujit Goyal, Trang Tran, Dhruvesh Patel, Michael Boratko, Shib Sankar Dasgupta, and Andrew McCallum. 2021. Box Embeddings: An open-source library for representation learning using geometric structures. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 203–211, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Box Embeddings: An open-source library for representation learning using geometric structures (Chheda et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-demo.24.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-demo.24.mp4
Code
 iesl/box-embeddings
Data
MultiNLI