← Search

Purujit Goyal

2 accepted papers

2022

Structured Energy Network As a Loss

NeurIPS 2022accept

Belanger & McCallum (2016) and Gygli et al. (2017) have shown that an energy network can capture arbitrary dependencies amongst the output variables in structured prediction; however, their reliance on gradient-based inference (GBI) makes the inference slow and unstable. In this work, we propose Str…

Cited by 4SourcePDFScholar
2021

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

EMNLP 2021system demonstrations

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 alt…