Introducing VULCAN: A Visualization Tool for Understanding Our Models and Data by Example

Jonas Groschwitz


Abstract
Examples are a powerful tool that help us understand complex concepts and connections. In computational linguistics research, looking at example system output and example corpus entries can offer a wealth of insights that are not otherwise accessible. This paper describes the open-source software VULCAN, a visualization tool for strings, graphs, trees, alignments, attention and more. VULCAN’s unique ability to visualize both linguistic structures and properties of neural models make it particularly relevant for neuro-symbolic models. Neuro-symbolic models, combining neural networks with often linguistically grounded structures, offer a promise of increased interpretability in an age of purely neural black-box end-to-end models. VULCAN aims to facilitate this interpretability in practice. VULCAN is designed to be both easy to use and powerful in its capabilities.
Anthology ID:
2023.blackboxnlp-1.15
Volume:
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2023
Address:
Singapore
Editors:
Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi
Venues:
BlackboxNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
199–211
Language:
URL:
https://aclanthology.org/2023.blackboxnlp-1.15
DOI:
10.18653/v1/2023.blackboxnlp-1.15
Bibkey:
Cite (ACL):
Jonas Groschwitz. 2023. Introducing VULCAN: A Visualization Tool for Understanding Our Models and Data by Example. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 199–211, Singapore. Association for Computational Linguistics.
Cite (Informal):
Introducing VULCAN: A Visualization Tool for Understanding Our Models and Data by Example (Groschwitz, BlackboxNLP-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.blackboxnlp-1.15.pdf